---
title: "From Static Inference to Dynamic Interaction: A Survey of"
description: "Most LLMs assume the entire input is available before they respond. 247 references, cited by 1 paper here."
authors: ["Junlong Tong", "Zilong Wang", "YuJie Ren", "Peiran Yin", "Hao Wu", "Wei Zhang", "Xiaoyu Shen"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.498/"
doi: "10.18653/v1/2026.findings-acl.498"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tong-2026-static-inference-dynamic-interaction-survey/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tong-2026-static-inference-dynamic-interaction-survey/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/13/) / From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models

# From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models

**Authors:** Junlong Tong, [Zilong Wang](https://md.research.elamur.ai/free/en/authors/zilong-wang/), [YuJie Ren](https://md.research.elamur.ai/free/en/authors/yujie-ren/), Peiran Yin, [Hao Wu](https://md.research.elamur.ai/free/en/authors/hao-wu/), [Wei Zhang](https://md.research.elamur.ai/free/en/authors/wei-zhang/) and [Xiaoyu Shen](https://md.research.elamur.ai/free/en/authors/xiaoyu-shen/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.498/) · [PDF](https://aclanthology.org/2026.findings-acl.498.pdf) · [DOI 10.18653/v1/2026.findings-acl.498](https://doi.org/10.18653/v1/2026.findings-acl.498) · [OpenAlex](https://openalex.org/W7166863479)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most LLMs assume the entire input is available before they respond. This assumption fails for live speech, video, simultaneous translation or agents, where data arrives piece by piece and may be unbounded. Prior work labelled "streaming LLM" has mixed together quite different ideas: token-by-token decoding, chunked encoding of inputs, and full-duplex systems such as GPT-4o.

This Findings of ACL 2026 survey by Tong et al. offers one formal definition based on data flow and on whether reading and writing overlap. A decision function determines which input prefix the model can see at each output step. From this, the authors derive three tiers: output-streaming, sequential-streaming and concurrent-streaming LLMs. Each tier inherits the difficulties of the previous one and adds new ones. Methods for text, speech and video are organised under this scheme, followed by a review of applications and open problems.

The paper reports no experiments. Its contribution is a common vocabulary and research roadmap, plus a maintained paper list (Awesome-Streaming-LLMs on GitHub).

## Key points
- **The three paradigms differ in how input is handled:**
  - *Output-streaming*: reads the full input at once, then generates incrementally.
  - *Sequential-streaming*: encodes input as it arrives, but answers only after the input ends.
  - *Concurrent-streaming*: reads and generates at the same time (full-duplex), with monotonic, partial input visibility.
- **Output-streaming work** covers:
  - Generation styles: token-wise, block-wise (semi-autoregressive SoT, block-diffusion SSD-LM, multi-scale VAR) and refinement-based (LLaDA, LaViDa).
  - Speed-ups: speculative decoding, AdaInfer and layer skipping, and memory savings via StreamingLLM.
- **Sequential-streaming work** covers:
  - Incremental encoding, either at fixed intervals (Whisper-Streaming, LLM-SimulMT) or semantically driven (DiSeg, CTC).
  - Context management: memory retention (Flash-VStream), attention-aware KV eviction (StreamKV, StreamingVLM) and compression (KIVI, ZipCache).
- **Concurrent-streaming work** covers:
  - Four architecture types: re-encoding (Simul-LLM), concatenated (Qwen3-Omni, Mini-Omni), interleaved (VideoLLM-online, CosyVoice 2, LiveCC) and group (StreamingThinker).
  - Interaction policies that are rule-based, SFT-based or RL-based.
  - Tasks split into perception-level (X→Y, e.g. translation, ASR) and cognition-level (X→Z→Y, e.g. reasoning, tool use).
- **Proposed future directions** include:
  - Proactive read/write policies and interpretability of streaming behaviour.
  - Omni-modal parallel streams.
  - Deeper concurrency: 3-level (perceive, reason, generate) and 4-level (adding tool use).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 149 works · 16,161 citations
- [Eastern Institute of Technology, Ningbo](https://md.research.elamur.ai/free/en/universities/eastern-institute-of-technology-ningbo/) — University, Ningbo, China · 3 works · 23 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin, Hao Wu, Wei Zhang and Xiaoyu Shen. 2026. From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{tong2026static,
  title = {{From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models}},
  author = {Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin, Hao Wu, Wei Zhang and Xiaoyu Shen},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.498},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.498}
}
```

- [← previous From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization](https://md.research.elamur.ai/free/en/papers/zhou-2026-signal-degradation-computation-collapse-uncovering/)
- [next → From Trial by Fire to Sleep like a Baby: A Lexicon of Anxiety Associations for 20K English Multi-Word Expressions](https://md.research.elamur.ai/free/en/papers/mohammad-2026-trial-fire-sleep-like-baby/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/13/)

## References

247 references, 38 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Victor Agostinelli, Max Wild, Matthew Raffel, Kazi Fuad, and Lizhong Chen. 2024. Simul-llm: A framework for exploring high-quality simultaneous translation with large language models. In Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers),… [find](https://scholar.google.com/scholar?q=Victor+Agostinelli%2C+Max+Wild%2C+Matthew+Raffel%2C+Kazi+Fuad%2C+and+Lizhong+Chen%2E+2024%2E+Simul%2Dllm%3A+A+framework+for+exploring+high%2Dquality+simultaneous+translation+with+large+language+models%2E+In+Proceedings+o)
2. Elad Amrani, Leonid Karlinsky, and Alex Bronstein. 2025. Sample-and parameter-efficient autoregressive image models. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 30127–30136. [find](https://scholar.google.com/scholar?q=Elad+Amrani%2C+Leonid+Karlinsky%2C+and+Alex+Bronstein%2E+2025%2E+Sample%2Dand+parameter%2Defficient+autoregressive+image+models%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition+Conference%2C+pages+301)
3. Chenxin An, Fei Huang, Jun Zhang, Shansan Gong, Xipeng Qiu, Chang Zhou, and Lingpeng Kong. 2024. Training-free long-context scaling of large language models. arXiv preprint arXiv:2402.17463. — [arXiv:2402.17463](https://arxiv.org/abs/2402.17463) [find](https://scholar.google.com/scholar?q=Chenxin+An%2C+Fei+Huang%2C+Jun+Zhang%2C+Shansan+Gong%2C+Xipeng+Qiu%2C+Chang+Zhou%2C+and+Lingpeng+Kong%2E+2024%2E+Training%2Dfree+long%2Dcontext+scaling+of+large+language+models%2E+arXiv+preprint+arXiv%3A2402%2E17463%2E+%E2%80%94+%5BarXiv%3A)
4. Zalán Borsos, Raphaël Marinier, Damien Vincent, Eugene Kharitonov, Olivier Pietquin, Matt Sharifi, Dominik Roblek, Olivier Teboul, David Grangier, Marco Tagliasacchi, et al. 2023a. [Audiolm: a language modeling approach to audio generation](https://md.research.elamur.ai/free/en/papers/borsos-2022-audiolm-language-modeling-approach-audio/). IEEE/ACM transactions on audio, speech, and language process…
5. Zalán Borsos, Matt Sharifi, Damien Vincent, Eugene Kharitonov, Neil Zeghidour, and Marco Tagliasacchi. 2023b. Soundstorm: Efficient parallel audio generation. arXiv preprint arXiv:2305.09636. — [arXiv:2305.09636](https://arxiv.org/abs/2305.09636) [find](https://scholar.google.com/scholar?q=Zal%C3%A1n+Borsos%2C+Matt+Sharifi%2C+Damien+Vincent%2C+Eugene+Kharitonov%2C+Neil+Zeghidour%2C+and+Marco+Tagliasacchi%2E+2023b%2E+Soundstorm%3A+Efficient+parallel+audio+generation%2E+arXiv+preprint+arXiv%3A2305%2E09636%2E+%E2%80%94+%5BarXiv)
6. Davide Caffagni, Federico Cocchi, Luca Barsellotti, Nicholas Moratelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia, and Rita Cucchiara. 2024. The revolution of multimodal [large language models: a survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). arXiv preprint arXiv:2402.12451.
7. Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D Lee, Deming Chen, and Tri Dao. 2024a. [Medusa: Simple llm inference acceleration framework with multiple decoding heads](https://md.research.elamur.ai/free/en/papers/cai-2024-medusa-simple-llm-inference-acceleration/). arXiv preprint arXiv:2401.10774.
8. Zefan Cai, Yichi Zhang, Bofei Gao, Yuliang Liu, Yucheng Li, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Junjie Hu, and Xiao Wen. 2024b. [Pyramidkv: Dynamic kv cache compression based on pyramidal information funneling](https://md.research.elamur.ai/free/en/papers/cai-2024-pyramidkv-dynamic-kv-cache-compression/). arXiv preprint arXiv:2406.02069.
9. Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T Freeman, Michael Rubinstein, et al. 2023. Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704. — [arXiv:2301.00704](https://arxiv.org/abs/2301.00704) [find](https://scholar.google.com/scholar?q=Huiwen+Chang%2C+Han+Zhang%2C+Jarred+Barber%2C+AJ+Maschinot%2C+Jose+Lezama%2C+Lu+Jiang%2C+Ming%2DHsuan+Yang%2C+Kevin+Murphy%2C+William+T+Freeman%2C+Michael+Rubinstein%2C+et+al%2E+2023%2E+Muse%3A+Text%2Dto%2Dimage+generation+via+maske)
10. Siddhant Arora, Haidar Khan, Kai Sun, Xin Luna Dong, Sajal Choudhary, Seungwhan Moon, Xinyuan Zhang, Adithya Sagar, Surya Teja Appini, Kaushik Patnaik, et al. 2025. Stream rag: Instant and accurate spoken dialogue systems with streaming tool usage. arXiv preprint arXiv:2510.02044. — [arXiv:2510.02044](https://arxiv.org/abs/2510.02044) [find](https://scholar.google.com/scholar?q=Siddhant+Arora%2C+Haidar+Khan%2C+Kai+Sun%2C+Xin+Luna+Dong%2C+Sajal+Choudhary%2C+Seungwhan+Moon%2C+Xinyuan+Zhang%2C+Adithya+Sagar%2C+Surya+Teja+Appini%2C+Kaushik+Patnaik%2C+et+al%2E+2025%2E+Stream+rag%3A+Instant+and+accurate+sp)
11. Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T Freeman. 2022. Maskgit: Masked generative image transformer. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11315–11325. [find](https://scholar.google.com/scholar?q=Huiwen+Chang%2C+Han+Zhang%2C+Lu+Jiang%2C+Ce+Liu%2C+and+William+T+Freeman%2E+2022%2E+Maskgit%3A+Masked+generative+image+transformer%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+recogniti)
12. Marianne Arriola, Aaron Gokaslan, Justin T Chiu, Zhihan Yang, Zhixuan Qi, Jiaqi Han, Subham Sekhar Sahoo, and Volodymyr Kuleshov. 2025. Block diffusion: Interpolating between autoregressive and diffusion language models. arXiv preprint arXiv:2503.09573. — [arXiv:2503.09573](https://arxiv.org/abs/2503.09573) [find](https://scholar.google.com/scholar?q=Marianne+Arriola%2C+Aaron+Gokaslan%2C+Justin+T+Chiu%2C+Zhihan+Yang%2C+Zhixuan+Qi%2C+Jiaqi+Han%2C+Subham+Sekhar+Sahoo%2C+and+Volodymyr+Kuleshov%2E+2025%2E+Block+diffusion%3A+Interpolating+between+autoregressive+and+diffus)
13. Dibyadip Chatterjee, Edoardo Remelli, Yale Song, Bugra Tekin, Abhay Mittal, Bharat Bhatnagar, Necati Cihan Camgoz, Shreyas Hampali, Eric Sauser, Shugao Ma, et al. 2025. Streaming videollms for real-time procedural video understanding. In Proceedings of the IEEE/CVF International Conference on Comput… [find](https://scholar.google.com/scholar?q=Dibyadip+Chatterjee%2C+Edoardo+Remelli%2C+Yale+Song%2C+Bugra+Tekin%2C+Abhay+Mittal%2C+Bharat+Bhatnagar%2C+Necati+Cihan+Camgoz%2C+Shreyas+Hampali%2C+Eric+Sauser%2C+Shugao+Ma%2C+et+al%2E+2025%2E+Streaming+videollms+for+real%2Dti)
14. Jacob Austin, Daniel D. Johnson, Jonathan Ho, Daniel Tarlow, and Aaron van den Oord. 2021. [Structured denoising diffusion models in discrete state-spaces](https://md.research.elamur.ai/free/en/papers/austin-2021-structured-denoising-diffusion-models-discrete/). arXiv preprint arXiv:2107.03006.
15. Richard He Bai, Zijin Gu, Tatiana Likhomanenko, and Navdeep Jaitly. 2025. Speakstream: Streaming text-to-speech with interleaved data. arXiv preprint arXiv:2505.19206. — [arXiv:2505.19206](https://arxiv.org/abs/2505.19206) [find](https://scholar.google.com/scholar?q=Richard+He+Bai%2C+Zijin+Gu%2C+Tatiana+Likhomanenko%2C+and+Navdeep+Jaitly%2E+2025%2E+Speakstream%3A+Streaming+text%2Dto%2Dspeech+with+interleaved+data%2E+arXiv+preprint+arXiv%3A2505%2E19206%2E+%E2%80%94+%5BarXiv%3A2505%2E19206%5D%28https%3A%2F%2Farx)
16. Richard He Bai, Tatiana Likhomanenko, Ruixiang Zhang, Zijin Gu, Zakaria Aldeneh, and Navdeep Jaitly. 2024. dmel: Speech tokenization made simple. arXiv preprint arXiv:2407.15835. — [arXiv:2407.15835](https://arxiv.org/abs/2407.15835) [find](https://scholar.google.com/scholar?q=Richard+He+Bai%2C+Tatiana+Likhomanenko%2C+Ruixiang+Zhang%2C+Zijin+Gu%2C+Zakaria+Aldeneh%2C+and+Navdeep+Jaitly%2E+2024%2E+dmel%3A+Speech+tokenization+made+simple%2E+arXiv+preprint+arXiv%3A2407%2E15835%2E+%E2%80%94+%5BarXiv%3A2407%2E15835%5D%28)
17. Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin Qinghong Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, Dongxing Mao, and Mike Zheng Shou. 2024a. Videollm-online: Online video large language model for streaming video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogniti… [find](https://scholar.google.com/scholar?q=Joya+Chen%2C+Zhaoyang+Lv%2C+Shiwei+Wu%2C+Kevin+Qinghong+Lin%2C+Chenan+Song%2C+Difei+Gao%2C+Jia%2DWei+Liu%2C+Ziteng+Gao%2C+Dongxing+Mao%2C+and+Mike+Zheng+Shou%2E+2024a%2E+Videollm%2Donline%3A+Online+video+large+language+model+for)
18. Joya Chen, Ziyun Zeng, Yiqi Lin, Wei Li, Zejun Ma, and Mike Zheng Shou. 2025a. Livecc: Learning video llm with streaming speech transcription at scale. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 29083–29095. [find](https://scholar.google.com/scholar?q=Joya+Chen%2C+Ziyun+Zeng%2C+Yiqi+Lin%2C+Wei+Li%2C+Zejun+Ma%2C+and+Mike+Zheng+Shou%2E+2025a%2E+Livecc%3A+Learning+video+llm+with+streaming+speech+transcription+at+scale%2E+In+Proceedings+of+the+Computer+Vision+and+Patter)
19. Xinjie Chen, Kai Fan, Wei Luo, Linlin Zhang, Libo Zhao, Xinggao Liu, and Zhongqiang Huang. 2024b. Divergence-guided simultaneous speech translation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17799–17807. [find](https://scholar.google.com/scholar?q=Xinjie+Chen%2C+Kai+Fan%2C+Wei+Luo%2C+Linlin+Zhang%2C+Libo+Zhao%2C+Xinggao+Liu%2C+and+Zhongqiang+Huang%2E+2024b%2E+Divergence%2Dguided+simultaneous+speech+translation%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial)
20. Xueyi Chen, Keda Tao, Kele Shao, and Huan Wang. 2025b. Streamingtom: Streaming token compression for efficient video understanding. arXiv preprint arXiv:2510.18269. — [arXiv:2510.18269](https://arxiv.org/abs/2510.18269) [find](https://scholar.google.com/scholar?q=Xueyi+Chen%2C+Keda+Tao%2C+Kele+Shao%2C+and+Huan+Wang%2E+2025b%2E+Streamingtom%3A+Streaming+token+compression+for+efficient+video+understanding%2E+arXiv+preprint+arXiv%3A2510%2E18269%2E+%E2%80%94+%5BarXiv%3A2510%2E18269%5D%28https%3A%2F%2Farxiv%2E)
21. Yilong Chen, Xiang Bai, Zhibin Wang, Chengyu Bai, Yuhan Dai, Ming Lu, and Shanghang Zhang. 2025c. Streamkv: Streaming video question-answering with segment-based kv cache retrieval and compression. arXiv preprint arXiv:2511.07278. — [arXiv:2511.07278](https://arxiv.org/abs/2511.07278) [find](https://scholar.google.com/scholar?q=Yilong+Chen%2C+Xiang+Bai%2C+Zhibin+Wang%2C+Chengyu+Bai%2C+Yuhan+Dai%2C+Ming+Lu%2C+and+Shanghang+Zhang%2E+2025c%2E+Streamkv%3A+Streaming+video+question%2Danswering+with+segment%2Dbased+kv+cache+retrieval+and+compression%2E+ar)
22. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024c. [Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks](https://md.research.elamur.ai/free/en/papers/chen-2023-internvl-scaling-up-vision/). In Proceedings of the IEEE/CVF conference on computer vision and pattern…
23. Zhuohan Chen, Yizhe Zhang, Ziyang Chen, Yuhao Lin, Songlin Wang, Hao Li, Kurt Keutzer, Joseph E Gonzalez, Michael W Mahoney, and Ion Stoica. 2023. Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318. [find](https://scholar.google.com/scholar?q=Zhuohan+Chen%2C+Yizhe+Zhang%2C+Ziyang+Chen%2C+Yuhao+Lin%2C+Songlin+Wang%2C+Hao+Li%2C+Kurt+Keutzer%2C+Joseph+E+Gonzalez%2C+Michael+W+Mahoney%2C+and+Ion+Stoica%2E+2023%2E+Accelerating+large+language+model+decoding+with+specu)
24. Jian Cheng, Haidong Kang, Yuxin Shao, Nan Li, Pengjun Chen, Rui Wang, Saiqin Long, Xiaochun Yang, and Lianbo Ma. 2025a. Survey on efficient large language models: Principles, algorithms, applications, and open issues. IEEE Transactions on Neural Networks and Learning Systems. [find](https://scholar.google.com/scholar?q=Jian+Cheng%2C+Haidong+Kang%2C+Yuxin+Shao%2C+Nan+Li%2C+Pengjun+Chen%2C+Rui+Wang%2C+Saiqin+Long%2C+Xiaochun+Yang%2C+and+Lianbo+Ma%2E+2025a%2E+Survey+on+efficient+large+language+models%3A+Principles%2C+algorithms%2C+applications%2C)
25. Shanbo Cheng, Yu Bao, Zhichao Huang, Yu Lu, Ningxin Peng, Lu Xu, Runsheng Yu, Rong Cao, Yujiao Du, Ting Han, et al. 2025b. Seed liveinterpret 2.0: End-to-end simultaneous speech-to-speech translation with your voice. arXiv preprint arXiv:2507.17527. — [arXiv:2507.17527](https://arxiv.org/abs/2507.17527) [find](https://scholar.google.com/scholar?q=Shanbo+Cheng%2C+Yu+Bao%2C+Zhichao+Huang%2C+Yu+Lu%2C+Ningxin+Peng%2C+Lu+Xu%2C+Runsheng+Yu%2C+Rong+Cao%2C+Yujiao+Du%2C+Ting+Han%2C+et+al%2E+2025b%2E+Seed+liveinterpret+2%2E0%3A+End%2Dto%2Dend+simultaneous+speech%2Dto%2Dspeech+translation+)
26. Ethan Chern, Jiadi Su, Yan Ma, and Pengfei Liu. 2024. Anole: An open, autoregressive, native large multimodal models for interleaved image-text generation. arXiv preprint arXiv:2407.06135. — [arXiv:2407.06135](https://arxiv.org/abs/2407.06135) [find](https://scholar.google.com/scholar?q=Ethan+Chern%2C+Jiadi+Su%2C+Yan+Ma%2C+and+Pengfei+Liu%2E+2024%2E+Anole%3A+An+open%2C+autoregressive%2C+native+large+multimodal+models+for+interleaved+image%2Dtext+generation%2E+arXiv+preprint+arXiv%3A2407%2E06135%2E+%E2%80%94+%5BarXiv%3A24)
27. Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie Liu, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, and Lijuan Wang. 2025a. Shanks: Simultaneous hearing and thinking for spoken language models. arXiv preprint arXiv:2510.06917. [find](https://scholar.google.com/scholar?q=Cheng%2DHan+Chiang%2C+Xiaofei+Wang%2C+Linjie+Li%2C+Chung%2DChing+Lin%2C+Kevin+Lin%2C+Shujie+Liu%2C+Zhendong+Wang%2C+Zhengyuan+Yang%2C+Hung%2Dyi+Lee%2C+and+Lijuan+Wang%2E+2025a%2E+Shanks%3A+Simultaneous+hearing+and+thinking+for+spo)
28. Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie Liu, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, and Lijuan Wang. 2025b. Stitch: Simultaneous thinking and talking with chunked reasoning for spoken language models. arXiv preprint arXiv:2507.15375. — [arXiv:2507.15375](https://arxiv.org/abs/2507.15375) [find](https://scholar.google.com/scholar?q=Cheng%2DHan+Chiang%2C+Xiaofei+Wang%2C+Linjie+Li%2C+Chung%2DChing+Lin%2C+Kevin+Lin%2C+Shujie+Liu%2C+Zhendong+Wang%2C+Zhengyuan+Yang%2C+Hung%2Dyi+Lee%2C+and+Lijuan+Wang%2E+2025b%2E+Stitch%3A+Simultaneous+thinking+and+talking+with+ch)
29. Marco Comunità, Zhi Zhong, Akira Takahashi, Shiqi Yang, Mengjie Zhao, Koichi Saito, Yukara Ikemiya, Takashi Shibuya, Shusuke Takahashi, and Yuki Mitsufuji. 2024. Specmaskgit: Masked generative modeling of audio spectrograms for efficient audio synthesis and beyond. arXiv preprint arXiv:2406.17672. [find](https://scholar.google.com/scholar?q=Marco+Comunit%C3%A0%2C+Zhi+Zhong%2C+Akira+Takahashi%2C+Shiqi+Yang%2C+Mengjie+Zhao%2C+Koichi+Saito%2C+Yukara+Ikemiya%2C+Takashi+Shibuya%2C+Shusuke+Takahashi%2C+and+Yuki+Mitsufuji%2E+2024%2E+Specmaskgit%3A+Masked+generative+modelin)
30. Anonymous Contributors. 2024. Llamagen: Large language model for continuous image generation. Open-source implementation; inspired by VQ-less LLM architecture for image generation. [find](https://scholar.google.com/scholar?q=Anonymous+Contributors%2E+2024%2E+Llamagen%3A+Large+language+model+for+continuous+image+generation%2E+Open%2Dsource+implementation%3B+inspired+by+VQ%2Dless+LLM+architecture+for+image+generation%2E)
31. Trung Dang, David Aponte, Dung Tran, and Kazuhito Koishida. 2024. Livespeech: Low-latency zero-shot text-to-speech via autoregressive modeling of audio discrete codes. arXiv preprint arXiv:2406.02897. — [arXiv:2406.02897](https://arxiv.org/abs/2406.02897) [find](https://scholar.google.com/scholar?q=Trung+Dang%2C+David+Aponte%2C+Dung+Tran%2C+and+Kazuhito+Koishida%2E+2024%2E+Livespeech%3A+Low%2Dlatency+zero%2Dshot+text%2Dto%2Dspeech+via+autoregressive+modeling+of+audio+discrete+codes%2E+arXiv+preprint+arXiv%3A2406%2E02897%2E)
32. Pierre V Dantas, Lucas C Cordeiro, and Waldir SS Junior. 2025. A review of state-of-the-art techniques for large language model compression. Complex & Intelligent Systems, 11(9):407. [find](https://scholar.google.com/scholar?q=Pierre+V+Dantas%2C+Lucas+C+Cordeiro%2C+and+Waldir+SS+Junior%2E+2025%2E+A+review+of+state%2Dof%2Dthe%2Dart+techniques+for+large+language+model+compression%2E+Complex+%26+Intelligent+Systems%2C+11%289%29%3A407%2E)
33. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+et+al%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437%2E)
34. Alexandre Défossez, Laurent Mazaré, Manu Orsini, Amélie Royer, Patrick Pérez, Hervé Jégou, Edouard Grave, and Neil Zeghidour. 2024. [Moshi: a speech-text foundation model for real-time dialogue](https://md.research.elamur.ai/free/en/papers/defossez-2024-moshi-speech-text-foundation-model/). arXiv preprint arXiv:2410.00037.
35. Luciano Del Corro, Allie Del Giorno, Sahaj Agarwal, Bin Yu, Ahmed Awadallah, and Subhabrata Mukherjee. 2023. Skipdecode: Autoregressive skip decoding with batching and caching for efficient llm inference. arXiv preprint arXiv:2307.02628. — [arXiv:2307.02628](https://arxiv.org/abs/2307.02628) [find](https://scholar.google.com/scholar?q=Luciano+Del+Corro%2C+Allie+Del+Giorno%2C+Sahaj+Agarwal%2C+Bin+Yu%2C+Ahmed+Awadallah%2C+and+Subhabrata+Mukherjee%2E+2023%2E+Skipdecode%3A+Autoregressive+skip+decoding+with+batching+and+caching+for+efficient+llm+infere)
36. Keqi Deng, Wenxi Chen, Xie Chen, and Phil Woodland. 2025. Simuls2s-llm: Unlocking simultaneous inference of speech llms for speech-to-speech translation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16718–16734. [find](https://scholar.google.com/scholar?q=Keqi+Deng%2C+Wenxi+Chen%2C+Xie+Chen%2C+and+Phil+Woodland%2E+2025%2E+Simuls2s%2Dllm%3A+Unlocking+simultaneous+inference+of+speech+llms+for+speech%2Dto%2Dspeech+translation%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+t)
37. Ding Ding, Zeqian Ju, Yichong Leng, Songxiang Liu, Tong Liu, Zeyu Shang, Kai Shen, Wei Song, Xu Tan, Heyi Tang, et al. 2025a. [Kimi-audio technical report](https://md.research.elamur.ai/free/en/papers/kimiteam-2025-kimi-audio-technical-report/). arXiv preprint arXiv:2504.18425.
38. Xin Ding, Hao Wu, Yifan Yang, Shiqi Jiang, Qianxi Zhang, Donglin Bai, Zhibo Chen, and Ting Cao. 2025b. Streammind: Unlocking full frame rate streaming video dialogue through event-gated cognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13448– 13459. [find](https://scholar.google.com/scholar?q=Xin+Ding%2C+Hao+Wu%2C+Yifan+Yang%2C+Shiqi+Jiang%2C+Qianxi+Zhang%2C+Donglin+Bai%2C+Zhibo+Chen%2C+and+Ting+Cao%2E+2025b%2E+Streammind%3A+Unlocking+full+frame+rate+streaming+video+dialogue+through+event%2Dgated+cognition%2E+In+)
39. Haotian Dong, Ye Li, Rongwei Lu, Chen Tang, Shu-Tao Xia, and Zhi Wang. 2025. Vvs: Accelerating speculative decoding for visual autoregressive generation via partial verification skipping. arXiv preprint arXiv:2511.13587. — [arXiv:2511.13587](https://arxiv.org/abs/2511.13587) [find](https://scholar.google.com/scholar?q=Haotian+Dong%2C+Ye+Li%2C+Rongwei+Lu%2C+Chen+Tang%2C+Shu%2DTao+Xia%2C+and+Zhi+Wang%2E+2025%2E+Vvs%3A+Accelerating+speculative+decoding+for+visual+autoregressive+generation+via+partial+verification+skipping%2E+arXiv+prepri)
40. Alexey Dosovitskiy. 2020. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). arXiv preprint arXiv:2010.11929.
41. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, et al. 2024. Cosyvoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint arXiv:2412.10117. [find](https://scholar.google.com/scholar?q=Zhihao+Du%2C+Yuxuan+Wang%2C+Qian+Chen%2C+Xian+Shi%2C+Xiang+Lv%2C+Tianyu+Zhao%2C+Zhifu+Gao%2C+Yexin+Yang%2C+Changfeng+Gao%2C+Hui+Wang%2C+et+al%2E+2024%2E+Cosyvoice+2%3A+Scalable+streaming+speech+synthesis+with+large+language+mo)
42. Shenghao Fu, Qize Yang, Yuan-Ming Li, Yi-Xing Peng, Kun-Yu Lin, Xihan Wei, Jian-Fang Hu, Xiaohua Xie, and Wei-Shi Zheng. 2025c. Vispeak: Visual instruction feedback in streaming videos. arXiv preprint arXiv:2503.12769. — [arXiv:2503.12769](https://arxiv.org/abs/2503.12769) [find](https://scholar.google.com/scholar?q=Shenghao+Fu%2C+Qize+Yang%2C+Yuan%2DMing+Li%2C+Yi%2DXing+Peng%2C+Kun%2DYu+Lin%2C+Xihan+Wei%2C+Jian%2DFang+Hu%2C+Xiaohua+Xie%2C+and+Wei%2DShi+Zheng%2E+2025c%2E+Vispeak%3A+Visual+instruction+feedback+in+streaming+videos%2E+arXiv+preprint)
43. Siqi Fan, Xin Jiang, Xiang Li, Xuying Meng, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang, and Zhongyuan Wang. 2024. Not all layers of llms are necessary during inference. arXiv preprint arXiv:2403.02181. — [arXiv:2403.02181](https://arxiv.org/abs/2403.02181) [find](https://scholar.google.com/scholar?q=Siqi+Fan%2C+Xin+Jiang%2C+Xiang+Li%2C+Xuying+Meng%2C+Peng+Han%2C+Shuo+Shang%2C+Aixin+Sun%2C+Yequan+Wang%2C+and+Zhongyuan+Wang%2E+2024%2E+Not+all+layers+of+llms+are+necessary+during+inference%2E+arXiv+preprint+arXiv%3A2403%2E021)
44. Yu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong, and Wen Xiao. 2024b. Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning. arXiv preprint arXiv:2410.19258. — [arXiv:2410.19258](https://arxiv.org/abs/2410.19258) [find](https://scholar.google.com/scholar?q=Yu+Fu%2C+Zefan+Cai%2C+Abedelkadir+Asi%2C+Wayne+Xiong%2C+Yue+Dong%2C+and+Wen+Xiao%2E+2024b%2E+Not+all+heads+matter%3A+A+head%2Dlevel+kv+cache+compression+method+with+integrated+retrieval+and+reasoning%2E+arXiv+preprint+ar)
45. Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, and Xiaoyu Shen. 2025. Visipruner: Decoding discontinuous cross-modal dynamics for efficient multimodal llms. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18896–18913. [find](https://scholar.google.com/scholar?q=Yingqi+Fan%2C+Anhao+Zhao%2C+Jinlan+Fu%2C+Junlong+Tong%2C+Hui+Su%2C+Yijie+Pan%2C+Wei+Zhang%2C+and+Xiaoyu+Shen%2E+2025%2E+Visipruner%3A+Decoding+discontinuous+cross%2Dmodal+dynamics+for+efficient+multimodal+llms%2E+In+Proceedi)
46. Xiangxiang Gao, Weisheng Xie, Yiwei Xiang, and Feng Ji. 2025. Falcon: Faster and parallel inference of large language models through enhanced semi-autoregressive drafting and custom-designed decoding tree. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23933– 2394… [find](https://scholar.google.com/scholar?q=Xiangxiang+Gao%2C+Weisheng+Xie%2C+Yiwei+Xiang%2C+and+Feng+Ji%2E+2025%2E+Falcon%3A+Faster+and+parallel+inference+of+large+language+models+through+enhanced+semi%2Dautoregressive+drafting+and+custom%2Ddesigned+decoding+)
47. Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, and Yang Feng. 2024. Llama-omni: Seamless speech interaction with large language models. arXiv preprint arXiv:2409.06666. [find](https://scholar.google.com/scholar?q=Qingkai+Fang%2C+Shoutao+Guo%2C+Yan+Zhou%2C+Zhengrui+Ma%2C+Shaolei+Zhang%2C+and+Yang+Feng%2E+2024%2E+Llama%2Domni%3A+Seamless+speech+interaction+with+large+language+models%2E+arXiv+preprint+arXiv%3A2409%2E06666%2E)
48. Qingkai Fang, Yan Zhou, Shoutao Guo, Shaolei Zhang, and Yang Feng. 2025. Llama-omni2: Llm-based real-time spoken chatbot with autoregressive streaming speech synthesis. arXiv preprint arXiv:2505.02625. — [arXiv:2505.02625](https://arxiv.org/abs/2505.02625) [find](https://scholar.google.com/scholar?q=Qingkai+Fang%2C+Yan+Zhou%2C+Shoutao+Guo%2C+Shaolei+Zhang%2C+and+Yang+Feng%2E+2025%2E+Llama%2Domni2%3A+Llm%2Dbased+real%2Dtime+spoken+chatbot+with+autoregressive+streaming+speech+synthesis%2E+arXiv+preprint+arXiv%3A2505%2E02625)
49. Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, and S Kevin Zhou. 2024. Ada-kv: Optimizing kv cache eviction by adaptive budget allocation for efficient llm inference. arXiv preprint arXiv:2407.11550. — [arXiv:2407.11550](https://arxiv.org/abs/2407.11550) [find](https://scholar.google.com/scholar?q=Yuan+Feng%2C+Junlin+Lv%2C+Yukun+Cao%2C+Xike+Xie%2C+and+S+Kevin+Zhou%2E+2024%2E+Ada%2Dkv%3A+Optimizing+kv+cache+eviction+by+adaptive+budget+allocation+for+efficient+llm+inference%2E+arXiv+preprint+arXiv%3A2407%2E11550%2E+%E2%80%94+%5Ba)
50. Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, and S Kevin Zhou. 2025. Identify critical kv cache in llm inference from an output perturbation perspective. arXiv preprint arXiv:2502.03805. — [arXiv:2502.03805](https://arxiv.org/abs/2502.03805) [find](https://scholar.google.com/scholar?q=Yuan+Feng%2C+Junlin+Lv%2C+Yukun+Cao%2C+Xike+Xie%2C+and+S+Kevin+Zhou%2E+2025%2E+Identify+critical+kv+cache+in+llm+inference+from+an+output+perturbation+perspective%2E+arXiv+preprint+arXiv%3A2502%2E03805%2E+%E2%80%94+%5BarXiv%3A2502%2E0)
51. Markus Frohmann, Igor Sterner, Ivan Vulić, Benjamin Minixhofer, and Markus Schedl. 2024. Segment any text: A universal approach for robust, efficient and adaptable sentence segmentation. arXiv preprint arXiv:2406.16678. [find](https://scholar.google.com/scholar?q=Markus+Frohmann%2C+Igor+Sterner%2C+Ivan+Vulic%CC%81%2C+Benjamin+Minixhofer%2C+and+Markus+Schedl%2E+2024%2E+Segment+any+text%3A+A+universal+approach+for+robust%2C+efficient+and+adaptable+sentence+segmentation%2E+arXiv+prepri)
52. Biao Fu, Kai Fan, Minpeng Liao, Yidong Chen, Xiaodong Shi, and Zhongqiang Huang. 2024a. wav2vec-s: Adapting pre-trained speech models for streaming. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11465–11480. [find](https://scholar.google.com/scholar?q=Biao+Fu%2C+Kai+Fan%2C+Minpeng+Liao%2C+Yidong+Chen%2C+Xiaodong+Shi%2C+and+Zhongqiang+Huang%2E+2024a%2E+wav2vec%2Ds%3A+Adapting+pre%2Dtrained+speech+models+for+streaming%2E+In+Findings+of+the+Association+for+Computational+Li)
53. Biao Fu, Minpeng Liao, Kai Fan, Chengxi Li, Liang Zhang, Yidong Chen, and Xiaodong Shi. 2025a. Llms can achieve high-quality simultaneous machine translation as efficiently as offline. In Findings of the Association for Computational Linguistics: ACL 2025, pages 20372–20395. [find](https://scholar.google.com/scholar?q=Biao+Fu%2C+Minpeng+Liao%2C+Kai+Fan%2C+Chengxi+Li%2C+Liang+Zhang%2C+Yidong+Chen%2C+and+Xiaodong+Shi%2E+2025a%2E+Llms+can+achieve+high%2Dquality+simultaneous+machine+translation+as+efficiently+as+offline%2E+In+Findings+of+)
54. Biao Fu, Donglei Yu, Minpeng Liao, Chengxi Li, Yidong Chen, Kai Fan, and Xiaodong Shi. 2025b. Efficient and adaptive simultaneous speech translation with fully unidirectional architecture. arXiv preprint arXiv:2504.11809. — [arXiv:2504.11809](https://arxiv.org/abs/2504.11809) [find](https://scholar.google.com/scholar?q=Biao+Fu%2C+Donglei+Yu%2C+Minpeng+Liao%2C+Chengxi+Li%2C+Yidong+Chen%2C+Kai+Fan%2C+and+Xiaodong+Shi%2E+2025b%2E+Efficient+and+adaptive+simultaneous+speech+translation+with+fully+unidirectional+architecture%2E+arXiv+prepr)
55. Gemma Team. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295. [find](https://scholar.google.com/scholar?q=Gemma+Team%2E+2024%2E+Gemma%3A+Open+models+based+on+gemini+research+and+technology%2E+arXiv+preprint+arXiv%3A2403%2E08295%2E)
56. Marjan Ghazvininejad, Omer Levy, Yinhan Liu, and Luke Zettlemoyer. 2019. [Mask-predict: Parallel decoding of conditional masked language models](https://md.research.elamur.ai/free/en/papers/ghazvininejad-2019-mask-predict-parallel-decoding-conditional/). In Proceedings of EMNLP-IJCNLP.
57. In Gim, Seung-seob Lee, and Lin Zhong. 2024. Asynchronous llm function calling. arXiv preprint arXiv:2412.07017. — [arXiv:2412.07017](https://arxiv.org/abs/2412.07017) [find](https://scholar.google.com/scholar?q=In+Gim%2C+Seung%2Dseob+Lee%2C+and+Lin+Zhong%2E+2024%2E+Asynchronous+llm+function+calling%2E+arXiv+preprint+arXiv%3A2412%2E07017%2E+%E2%80%94+%5BarXiv%3A2412%2E07017%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E07017%29)
58. Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, et al. 2024. [Chatglm: A family of large language models from glm-130b to glm-4 all tools](https://md.research.elamur.ai/free/en/papers/glm-2024-chatglm-family-large-language-models/). arXiv preprint arXiv:2406.12793.
59. Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, and Gabriel Synnaeve. 2024. Better & faster large language models via multi-token prediction. arXiv preprint arXiv:2404.19737. [find](https://scholar.google.com/scholar?q=Fabian+Gloeckle%2C+Badr+Youbi+Idrissi%2C+Baptiste+Rozi%C3%A8re%2C+David+Lopez%2DPaz%2C+and+Gabriel+Synnaeve%2E+2024%2E+Better+%26+faster+large+language+models+via+multi%2Dtoken+prediction%2E+arXiv+preprint+arXiv%3A2404%2E19737%2E)
60. Chengyue Gong, Xuezhe Feng, Guanyi Qin, Yixin Liu, et al. 2022. Diffuseq: Sequence to sequence text generation with diffusion models. arXiv preprint arXiv:2210.08933. [find](https://scholar.google.com/scholar?q=Chengyue+Gong%2C+Xuezhe+Feng%2C+Guanyi+Qin%2C+Yixin+Liu%2C+et+al%2E+2022%2E+Diffuseq%3A+Sequence+to+sequence+text+generation+with+diffusion+models%2E+arXiv+preprint+arXiv%3A2210%2E08933%2E)
61. Alex Graves. 2012. Connectionist temporal classification. In Supervised sequence labelling with recurrent neural networks, pages 61–93. Springer. [find](https://scholar.google.com/scholar?q=Alex+Graves%2E+2012%2E+Connectionist+temporal+classification%2E+In+Supervised+sequence+labelling+with+recurrent+neural+networks%2C+pages+61%E2%80%9393%2E+Springer%2E)
62. Jiatao Gu, Changhan Wang, and Jake Zhao. 2019. Levenshtein transformer. In Advances in Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Jiatao+Gu%2C+Changhan+Wang%2C+and+Jake+Zhao%2E+2019%2E+Levenshtein+transformer%2E+In+Advances+in+Neural+Information+Processing+Systems+%28NeurIPS%29%2E)
63. Dake Guo, Jixun Yao, Linhan Ma, He Wang, and Lei Xie. 2025. Streamflow: Streaming flow matching with block-wise guided attention mask for speech token decoding. arXiv preprint arXiv:2506.23986. — [arXiv:2506.23986](https://arxiv.org/abs/2506.23986) [find](https://scholar.google.com/scholar?q=Dake+Guo%2C+Jixun+Yao%2C+Linhan+Ma%2C+He+Wang%2C+and+Lei+Xie%2E+2025%2E+Streamflow%3A+Streaming+flow+matching+with+block%2Dwise+guided+attention+mask+for+speech+token+decoding%2E+arXiv+preprint+arXiv%3A2506%2E23986%2E+%E2%80%94+%5BarX)
64. Hao-Han Guo, Yao Hu, Kun Liu, Fei-Yu Shen, Xu Tang, Yi-Chen Wu, Feng-Long Xie, Kun Xie, and Kai-Tuo Xu. 2024a. Fireredtts: A foundation text-to-speech framework for industry-level generative speech applications. arXiv preprint arXiv:2409.03283. — [arXiv:2409.03283](https://arxiv.org/abs/2409.03283) [find](https://scholar.google.com/scholar?q=Hao%2DHan+Guo%2C+Yao+Hu%2C+Kun+Liu%2C+Fei%2DYu+Shen%2C+Xu+Tang%2C+Yi%2DChen+Wu%2C+Feng%2DLong+Xie%2C+Kun+Xie%2C+and+Kai%2DTuo+Xu%2E+2024a%2E+Fireredtts%3A+A+foundation+text%2Dto%2Dspeech+framework+for+industry%2Dlevel+generative+speech+ap)
65. Shoutao Guo, Shaolei Zhang, and Yang Feng. 2024b. Decoder-only streaming transformer for simultaneous translation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8851–8864. [find](https://scholar.google.com/scholar?q=Shoutao+Guo%2C+Shaolei+Zhang%2C+and+Yang+Feng%2E+2024b%2E+Decoder%2Donly+streaming+transformer+for+simultaneous+translation%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computational+Lingui)
66. Hyeonbin Hwang, Byeongguk Jeon, Seungone Kim, Jiyeon Kim, Hoyeon Chang, Sohee Yang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo. 2025. Let’s predict sentence by sentence. arXiv preprint arXiv:2505.22202. — [arXiv:2505.22202](https://arxiv.org/abs/2505.22202) [find](https://scholar.google.com/scholar?q=Hyeonbin+Hwang%2C+Byeongguk+Jeon%2C+Seungone+Kim%2C+Jiyeon+Kim%2C+Hoyeon+Chang%2C+Sohee+Yang%2C+Seungpil+Won%2C+Dohaeng+Lee%2C+Youbin+Ahn%2C+and+Minjoon+Seo%2E+2025%2E+Let%E2%80%99s+predict+sentence+by+sentence%2E+arXiv+preprint+arX)
67. Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang, and Yang Feng. 2024c. Sillm: Large language models for simultaneous machine translation. arXiv preprint arXiv:2402.13036. — [arXiv:2402.13036](https://arxiv.org/abs/2402.13036) [find](https://scholar.google.com/scholar?q=Shoutao+Guo%2C+Shaolei+Zhang%2C+Zhengrui+Ma%2C+Min+Zhang%2C+and+Yang+Feng%2E+2024c%2E+Sillm%3A+Large+language+models+for+simultaneous+machine+translation%2E+arXiv+preprint+arXiv%3A2402%2E13036%2E+%E2%80%94+%5BarXiv%3A2402%2E13036%5D%28https)
68. Javier Iranzo-Sánchez, Jorge Iranzo-Sánchez, Adrià Giménez, Jorge Civera, and Alfons Juan. 2024. Segmentation-free streaming machine translation. Transactions of the Association for Computational Linguistics, 12:1104–1121. [find](https://scholar.google.com/scholar?q=Javier+Iranzo%2DS%C3%A1nchez%2C+Jorge+Iranzo%2DS%C3%A1nchez%2C+Adri%C3%A0+Gim%C3%A9nez%2C+Jorge+Civera%2C+and+Alfons+Juan%2E+2024%2E+Segmentation%2Dfree+streaming+machine+translation%2E+Transactions+of+the+Association+for+Computational+Ling)
69. Jian Han, Jinlai Liu, Yi Jiang, Bin Yan, Yuqi Zhang, Zehuan Yuan, Bingyue Peng, and Xiaobing Liu. 2025. Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 15733–15744. [find](https://scholar.google.com/scholar?q=Jian+Han%2C+Jinlai+Liu%2C+Yi+Jiang%2C+Bin+Yan%2C+Yuqi+Zhang%2C+Zehuan+Yuan%2C+Bingyue+Peng%2C+and+Xiaobing+Liu%2E+2025%2E+Infinity%3A+Scaling+bitwise+autoregressive+modeling+for+high%2Dresolution+image+synthesis%2E+In+Procee)
70. Xiaochuang Han, Sachin Kumar, and Yulia Tsvetkov. 2023. Ssd-lm: Semi-autoregressive simplex-based diffusion language model for text generation and modular control. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11575– 11596. [find](https://scholar.google.com/scholar?q=Xiaochuang+Han%2C+Sachin+Kumar%2C+and+Yulia+Tsvetkov%2E+2023%2E+Ssd%2Dlm%3A+Semi%2Dautoregressive+simplex%2Dbased+diffusion+language+model+for+text+generation+and+modular+control%2E+In+Proceedings+of+the+61st+Annual+Me)
71. Jiadong Hao, Bohan Zhang, Yuchen Lu, Chengcheng Zhang, and Kunda Yang. Stylle: Style learning and latent editing for stylized text and speech generation. [find](https://scholar.google.com/scholar?q=Jiadong+Hao%2C+Bohan+Zhang%2C+Yuchen+Lu%2C+Chengcheng+Zhang%2C+and+Kunda+Yang%2E+Stylle%3A+Style+learning+and+latent+editing+for+stylized+text+and+speech+generation%2E)
72. Yefei He, Luoming Zhang, Weijia Wu, Jing Liu, Hong Zhou, and Bohan Zhuang. 2024. Zipcache: Accurate and efficient kv cache quantization with salient token identification. Advances in Neural Information Processing Systems, 37:68287–68307. [find](https://scholar.google.com/scholar?q=Yefei+He%2C+Luoming+Zhang%2C+Weijia+Wu%2C+Jing+Liu%2C+Hong+Zhou%2C+and+Bohan+Zhuang%2E+2024%2E+Zipcache%3A+Accurate+and+efficient+kv+cache+quantization+with+salient+token+identification%2E+Advances+in+Neural+Informatio)
73. Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Michael W Mahoney, Yakun S Shao, Kurt Keutzer, and Amir Gholami. 2024. [Kvquant: Towards 10 million context length llm inference with kv cache quantization](https://md.research.elamur.ai/free/en/papers/hooper-2024-kvquant-towards-10-million-context/). Advances in Neural Information Processing Systems, 37:1270–1303.
74. Chihan Huang and Hao Tang. 2025. Ctrldiff: Boosting large diffusion language models with dynamic block prediction and controllable generation. arXiv preprint arXiv:2505.14455. — [arXiv:2505.14455](https://arxiv.org/abs/2505.14455) [find](https://scholar.google.com/scholar?q=Chihan+Huang+and+Hao+Tang%2E+2025%2E+Ctrldiff%3A+Boosting+large+diffusion+language+models+with+dynamic+block+prediction+and+controllable+generation%2E+arXiv+preprint+arXiv%3A2505%2E14455%2E+%E2%80%94+%5BarXiv%3A2505%2E14455%5D%28htt)
75. Kuan-Po Huang, Shu-wen Yang, Huy Phan, Bo-Ru Lu, Byeonggeun Kim, Sashank Macha, Qingming Tang, Shalini Ghosh, Hung-yi Lee, Chieh-Chi Kao, et al. 2025a. Impact: Iterative mask-based parallel decoding for text-to-audio generation with diffusion modeling. arXiv preprint arXiv:2506.00736. — [arXiv:2506.00736](https://arxiv.org/abs/2506.00736) [find](https://scholar.google.com/scholar?q=Kuan%2DPo+Huang%2C+Shu%2Dwen+Yang%2C+Huy+Phan%2C+Bo%2DRu+Lu%2C+Byeonggeun+Kim%2C+Sashank+Macha%2C+Qingming+Tang%2C+Shalini+Ghosh%2C+Hung%2Dyi+Lee%2C+Chieh%2DChi+Kao%2C+et+al%2E+2025a%2E+Impact%3A+Iterative+mask%2Dbased+parallel+decoding+f)
76. Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Yao Hu, and Shaohui Lin. 2024. Dynamic-llava: Efficient multimodal large language models via dynamic vision-language context sparsification. arXiv preprint arXiv:2412.00876. [find](https://scholar.google.com/scholar?q=Wenxuan+Huang%2C+Zijie+Zhai%2C+Yunhang+Shen%2C+Shaosheng+Cao%2C+Fei+Zhao%2C+Xiangfeng+Xu%2C+Zheyu+Ye%2C+Yao+Hu%2C+and+Shaohui+Lin%2E+2024%2E+Dynamic%2Dllava%3A+Efficient+multimodal+large+language+models+via+dynamic+vision%2Dla)
77. Xiaohu Huang, Hao Zhou, and Kai Han. 2025b. Prunevid: Visual token pruning for efficient video large language models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 19959–19973. [find](https://scholar.google.com/scholar?q=Xiaohu+Huang%2C+Hao+Zhou%2C+and+Kai+Han%2E+2025b%2E+Prunevid%3A+Visual+token+pruning+for+efficient+video+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2025%2C+pages+1995)
78. Doohyuk Jang, Sihwan Park, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu, Sung-Yub Kim, and Eunho Yang. 2024. Lantern: Accelerating visual autoregressive models with relaxed speculative decoding. arXiv preprint arXiv:2410.03355. — [arXiv:2410.03355](https://arxiv.org/abs/2410.03355) [find](https://scholar.google.com/scholar?q=Doohyuk+Jang%2C+Sihwan+Park%2C+June+Yong+Yang%2C+Yeonsung+Jung%2C+Jihun+Yun%2C+Souvik+Kundu%2C+Sung%2DYub+Kim%2C+and+Eunho+Yang%2E+2024%2E+Lantern%3A+Accelerating+visual+autoregressive+models+with+relaxed+speculative+decod)
79. Dongya Jia, Zhuo Chen, Jiawei Chen, Chenpeng Du, Jian Wu, Jian Cong, Xiaobin Zhuang, Chumin Li, Zhen Wei, Yuping Wang, and Yuxuan Wang. 2025. Ditar: Diffusion transformer autoregressive modeling for speech generation. In Proceedings of the 42nd International Conference on Machine Learning, volume 26… [find](https://scholar.google.com/scholar?q=Dongya+Jia%2C+Zhuo+Chen%2C+Jiawei+Chen%2C+Chenpeng+Du%2C+Jian+Wu%2C+Jian+Cong%2C+Xiaobin+Zhuang%2C+Chumin+Li%2C+Zhen+Wei%2C+Yuping+Wang%2C+and+Yuxuan+Wang%2E+2025%2E+Ditar%3A+Diffusion+transformer+autoregressive+modeling+for+s)
80. Xinqi Jin, Hanxun Yu, Bohan Yu, Kebin Liu, Jian Liu, Keda Tao, Yixuan Pei, Huan Wang, Fan Dang, Jiangchuan Liu, et al. 2025. Streamingassistant: Efficient visual token pruning for accelerating online video understanding. arXiv preprint arXiv:2512.12560. [find](https://scholar.google.com/scholar?q=Xinqi+Jin%2C+Hanxun+Yu%2C+Bohan+Yu%2C+Kebin+Liu%2C+Jian+Liu%2C+Keda+Tao%2C+Yixuan+Pei%2C+Huan+Wang%2C+Fan+Dang%2C+Jiangchuan+Liu%2C+et+al%2E+2025%2E+Streamingassistant%3A+Efficient+visual+token+pruning+for+accelerating+online+)
81. Sehoon Kim, Karttikeya Mangalam, Suhong Moon, Jitendra Malik, Michael W Mahoney, Amir Gholami, and Kurt Keutzer. 2023. Speculative decoding with big little decoder. Advances in Neural Information Processing Systems, 36:39236–39256. [find](https://scholar.google.com/scholar?q=Sehoon+Kim%2C+Karttikeya+Mangalam%2C+Suhong+Moon%2C+Jitendra+Malik%2C+Michael+W+Mahoney%2C+Amir+Gholami%2C+and+Kurt+Keutzer%2E+2023%2E+Speculative+decoding+with+big+little+decoder%2E+Advances+in+Neural+Information+Proc)
82. Dan Kondratyuk, Lijun Yu, Xiuye Gu, Jose Lezama, Jonathan Huang, Grant Schindler, Rachel Hornung, Vighnesh Birodkar, Jimmy Yan, Ming-Chang Chiu, et al. 2024. Videopoet: A large language model for zero-shot video generation. In International Conference on Machine Learning, pages 25105–25124. PMLR. [find](https://scholar.google.com/scholar?q=Dan+Kondratyuk%2C+Lijun+Yu%2C+Xiuye+Gu%2C+Jose+Lezama%2C+Jonathan+Huang%2C+Grant+Schindler%2C+Rachel+Hornung%2C+Vighnesh+Birodkar%2C+Jimmy+Yan%2C+Ming%2DChang+Chiu%2C+et+al%2E+2024%2E+Videopoet%3A+A+large+language+model+for+zero)
83. Roman Koshkin, Katsuhito Sudoh, and Satoshi Nakamura. 2024a. Llms are zero-shot context-aware simultaneous translators. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1192–1207. [find](https://scholar.google.com/scholar?q=Roman+Koshkin%2C+Katsuhito+Sudoh%2C+and+Satoshi+Nakamura%2E+2024a%2E+Llms+are+zero%2Dshot+context%2Daware+simultaneous+translators%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Language+P)
84. Roman Koshkin, Katsuhito Sudoh, and Satoshi Nakamura. 2024b. Transllama: Llm-based simultaneous translation system. arXiv preprint arXiv:2402.04636. [find](https://scholar.google.com/scholar?q=Roman+Koshkin%2C+Katsuhito+Sudoh%2C+and+Satoshi+Nakamura%2E+2024b%2E+Transllama%3A+Llm%2Dbased+simultaneous+translation+system%2E+arXiv+preprint+arXiv%3A2402%2E04636%2E)
85. Pin-Jui Ku, He Huang, Jean-Marie Lemercier, Subham Sekhar Sahoo, Zhehuai Chen, and Ante Jukić. 2025. Discrete diffusion for generative modeling of text-aligned speech tokens. arXiv preprint arXiv:2509.20060. — [arXiv:2509.20060](https://arxiv.org/abs/2509.20060) [find](https://scholar.google.com/scholar?q=Pin%2DJui+Ku%2C+He+Huang%2C+Jean%2DMarie+Lemercier%2C+Subham+Sekhar+Sahoo%2C+Zhehuai+Chen%2C+and+Ante+Jukic%CC%81%2E+2025%2E+Discrete+diffusion+for+generative+modeling+of+text%2Daligned+speech+tokens%2E+arXiv+preprint+arXiv%3A250)
86. Taku Kudo. 2018. [Subword regularization: Improving neural network translation models with multiple subword candidates](https://md.research.elamur.ai/free/en/papers/kudo-2018-subword-regularization-improving-neural-network/). arXiv preprint arXiv:1804.10959.
87. Taku Kudo and John Richardson. 2018. [Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing](https://md.research.elamur.ai/free/en/papers/kudo-2018-sentencepiece-simple-language-independent-subword/). arXiv preprint arXiv:1808.06226.
88. Kunjun Li, Zigeng Chen, Cheng-Yen Yang, and Jenq-Neng Hwang. 2025e. Memory-efficient visual autoregressive modeling with scale-aware kv cache compression. arXiv preprint arXiv:2505.19602. — [arXiv:2505.19602](https://arxiv.org/abs/2505.19602) [find](https://scholar.google.com/scholar?q=Kunjun+Li%2C+Zigeng+Chen%2C+Cheng%2DYen+Yang%2C+and+Jenq%2DNeng+Hwang%2E+2025e%2E+Memory%2Defficient+visual+autoregressive+modeling+with+scale%2Daware+kv+cache+compression%2E+arXiv+preprint+arXiv%3A2505%2E19602%2E+%E2%80%94+%5BarXiv%3A250)
89. Chenyang Le, Bing Han, Jinshun Li, Songyong Chen, and Yanmin Qian. 2025. Simulmega: Moe routers are advanced policy makers for simultaneous speech translation. arXiv preprint arXiv:2509.01200. — [arXiv:2509.01200](https://arxiv.org/abs/2509.01200) [find](https://scholar.google.com/scholar?q=Chenyang+Le%2C+Bing+Han%2C+Jinshun+Li%2C+Songyong+Chen%2C+and+Yanmin+Qian%2E+2025%2E+Simulmega%3A+Moe+routers+are+advanced+policy+makers+for+simultaneous+speech+translation%2E+arXiv+preprint+arXiv%3A2509%2E01200%2E+%E2%80%94+%5BarXi)
90. Ruanjun Li, Yuedong Tan, Yuanming Shi, and Jiawei Shao. 2025f. Videoscan: Enabling efficient streaming video understanding via frame-level semantic carriers. arXiv preprint arXiv:2503.09387. [find](https://scholar.google.com/scholar?q=Ruanjun+Li%2C+Yuedong+Tan%2C+Yuanming+Shi%2C+and+Jiawei+Shao%2E+2025f%2E+Videoscan%3A+Enabling+efficient+streaming+video+understanding+via+frame%2Dlevel+semantic+carriers%2E+arXiv+preprint+arXiv%3A2503%2E09387%2E)
91. Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Yossi Adi, Jay Mahadeokar, et al. 2023. Voicebox: Text-guided multilingual universal speech generation at scale. Advances in neural information processing systems, 36:14005–14034. [find](https://scholar.google.com/scholar?q=Matthew+Le%2C+Apoorv+Vyas%2C+Bowen+Shi%2C+Brian+Karrer%2C+Leda+Sari%2C+Rashel+Moritz%2C+Mary+Williamson%2C+Vimal+Manohar%2C+Yossi+Adi%2C+Jay+Mahadeokar%2C+et+al%2E+2023%2E+Voicebox%3A+Text%2Dguided+multilingual+universal+speech+)
92. Shufan Li, Konstantinos Kallidromitis, Hritik Bansal, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Jason Kuen, Zhe Lin, Kai-Wei Chang, and Aditya Grover. 2025g. Lavida: A large diffusion language model for multimodal understanding. arXiv preprint arXiv:2505.16839. — [arXiv:2505.16839](https://arxiv.org/abs/2505.16839) [find](https://scholar.google.com/scholar?q=Shufan+Li%2C+Konstantinos+Kallidromitis%2C+Hritik+Bansal%2C+Akash+Gokul%2C+Yusuke+Kato%2C+Kazuki+Kozuka%2C+Jason+Kuen%2C+Zhe+Lin%2C+Kai%2DWei+Chang%2C+and+Aditya+Grover%2E+2025g%2E+Lavida%3A+A+large+diffusion+language+model+fo)
93. Haodong Lei, Hongsong Wang, Xin Geng, Liang Wang, and Pan Zhou. 2025. Fast inference of visual autoregressive model with adjacency-adaptive dynamical draft trees. arXiv preprint arXiv:2512.21857. — [arXiv:2512.21857](https://arxiv.org/abs/2512.21857) [find](https://scholar.google.com/scholar?q=Haodong+Lei%2C+Hongsong+Wang%2C+Xin+Geng%2C+Liang+Wang%2C+and+Pan+Zhou%2E+2025%2E+Fast+inference+of+visual+autoregressive+model+with+adjacency%2Dadaptive+dynamical+draft+trees%2E+arXiv+preprint+arXiv%3A2512%2E21857%2E+%E2%80%94+%5Ba)
94. Wei Li, Bing Hu, Rui Shao, Leyang Shen, and Liqiang Nie. 2025h. Lion-fs: Fast & slow video-language thinker as online video assistant. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3240–3251. [find](https://scholar.google.com/scholar?q=Wei+Li%2C+Bing+Hu%2C+Rui+Shao%2C+Leyang+Shen%2C+and+Liqiang+Nie%2E+2025h%2E+Lion%2Dfs%3A+Fast+%26+slow+video%2Dlanguage+thinker+as+online+video+assistant%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+)
95. Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In Proceedings of the 40th International Conference on Machine Learning (ICML). [find](https://scholar.google.com/scholar?q=Yaniv+Leviathan%2C+Matan+Kalman%2C+and+Yossi+Matias%2E+2023%2E+Fast+inference+from+transformers+via+speculative+decoding%2E+In+Proceedings+of+the+40th+International+Conference+on+Machine+Learning+%28ICML%29%2E)
96. Bohan Li, Zhihan Li, Haoran Wang, Hanglei Zhang, Yiwei Guo, Hankun Wang, Xie Chen, and Kai Yu. 2025a. Robust and efficient autoregressive speech synthesis with dynamic chunk-wise prediction policy. arXiv preprint arXiv:2506.22023. — [arXiv:2506.22023](https://arxiv.org/abs/2506.22023) [find](https://scholar.google.com/scholar?q=Bohan+Li%2C+Zhihan+Li%2C+Haoran+Wang%2C+Hanglei+Zhang%2C+Yiwei+Guo%2C+Hankun+Wang%2C+Xie+Chen%2C+and+Kai+Yu%2E+2025a%2E+Robust+and+efficient+autoregressive+speech+synthesis+with+dynamic+chunk%2Dwise+prediction+policy%2E+ar)
97. Bohan Li, Hankun Wang, Situo Zhang, Yiwei Guo, and Kai Yu. 2025b. Fast and high-quality autoregressive speech synthesis via speculative decoding. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. [find](https://scholar.google.com/scholar?q=Bohan+Li%2C+Hankun+Wang%2C+Situo+Zhang%2C+Yiwei+Guo%2C+and+Kai+Yu%2E+2025b%2E+Fast+and+high%2Dquality+autoregressive+speech+synthesis+via+speculative+decoding%2E+In+ICASSP+2025%2D2025+IEEE+International+Conference+on+A)
98. Han Li, Xinyu Peng, Yaoming Wang, Zelin Peng, Xin Chen, Rongxiang Weng, Jingang Wang, Xunliang Cai, Wenrui Dai, and Hongkai Xiong. 2025c. Onecat: Decoder-only auto-regressive model for unified understanding and generation. arXiv preprint arXiv:2509.03498. — [arXiv:2509.03498](https://arxiv.org/abs/2509.03498) [find](https://scholar.google.com/scholar?q=Han+Li%2C+Xinyu+Peng%2C+Yaoming+Wang%2C+Zelin+Peng%2C+Xin+Chen%2C+Rongxiang+Weng%2C+Jingang+Wang%2C+Xunliang+Cai%2C+Wenrui+Dai%2C+and+Hongkai+Xiong%2E+2025c%2E+Onecat%3A+Decoder%2Donly+auto%2Dregressive+model+for+unified+underst)
99. Xiang Lisa Li, John Thickstun Zhao, James Diffenderfer, Xuezhe He, Percy Liang, and Graham Neubig. 2022. [Diffusion-LM improves controllable text generation](https://md.research.elamur.ai/free/en/papers/li-2022-diffusion-lm-improves-controllable-text/). In Advances in Neural Information Processing Systems (NeurIPS).
100. Yang Li, Qiang Sheng, Yehan Yang, Xueyao Zhang, and Juan Cao. 2025i. From judgment to interference: Early stopping llm harmful outputs via streaming content monitoring. arXiv preprint arXiv:2506.09996. — [arXiv:2506.09996](https://arxiv.org/abs/2506.09996) [find](https://scholar.google.com/scholar?q=Yang+Li%2C+Qiang+Sheng%2C+Yehan+Yang%2C+Xueyao+Zhang%2C+and+Juan+Cao%2E+2025i%2E+From+judgment+to+interference%3A+Early+stopping+llm+harmful+outputs+via+streaming+content+monitoring%2E+arXiv+preprint+arXiv%3A2506%2E09996)
101. Ying Li, chengfei lv, and Huan Wang. 2025j. Freqexit: Enabling early-exit inference for visual autoregressive models via frequency-aware guidance. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Ying+Li%2C+chengfei+lv%2C+and+Huan+Wang%2E+2025j%2E+Freqexit%3A+Enabling+early%2Dexit+inference+for+visual+autoregressive+models+via+frequency%2Daware+guidance%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Infor)
102. Yuhong Li, Yingbing Huang, Bowen Yang, Bharat Venkitesh, Acyr Locatelli, Hanchen Ye, Tianle Cai, Patrick Lewis, and Deming Chen. 2024c. [Snapkv: Llm knows what you are looking for before generation](https://md.research.elamur.ai/free/en/papers/li-2024-snapkv-llm-knows-looking-before/). Advances in Neural Information Processing Systems, 37:22947–22970.
103. Haoyang Li, Yiming Li, Anxin Tian, Tianhao Tang, Zhanchao Xu, Xuejia Chen, Nicole Hu, Wei Dong, Qing Li, and Lei Chen. 2024a. A survey on large language model acceleration based on kv cache management. arXiv preprint arXiv:2412.19442. — [arXiv:2412.19442](https://arxiv.org/abs/2412.19442) [find](https://scholar.google.com/scholar?q=Haoyang+Li%2C+Yiming+Li%2C+Anxin+Tian%2C+Tianhao+Tang%2C+Zhanchao+Xu%2C+Xuejia+Chen%2C+Nicole+Hu%2C+Wei+Dong%2C+Qing+Li%2C+and+Lei+Chen%2E+2024a%2E+A+survey+on+large+language+model+acceleration+based+on+kv+cache+management)
104. Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024d. [Eagle-2: Faster inference of language models with dynamic draft trees](https://md.research.elamur.ai/free/en/papers/li-2024-eagle-2-faster-inference-language/). arXiv preprint arXiv:2406.16858.
105. Jia-Nan Li, Quan Tu, Cunli Mao, Zhengtao Yu, Ji-Rong Wen, and Rui Yan. 2024b. Streamingdialogue: Prolonged dialogue learning via long context compression with minimal losses. Advances in Neural Information Processing Systems, 37:86074–86101. [find](https://scholar.google.com/scholar?q=Jia%2DNan+Li%2C+Quan+Tu%2C+Cunli+Mao%2C+Zhengtao+Yu%2C+Ji%2DRong+Wen%2C+and+Rui+Yan%2E+2024b%2E+Streamingdialogue%3A+Prolonged+dialogue+learning+via+long+context+compression+with+minimal+losses%2E+Advances+in+Neural+Inform)
106. Zinuo Li, Xian Zhang, Yongxin Guo, Mohammed Bennamoun, Farid Boussaid, Girish Dwivedi, Luqi Gong, and Qiuhong Ke. 2025k. Watch and listen: Understanding audio-visual-speech moments with multimodal llm. arXiv preprint arXiv:2505.18110. — [arXiv:2505.18110](https://arxiv.org/abs/2505.18110) [find](https://scholar.google.com/scholar?q=Zinuo+Li%2C+Xian+Zhang%2C+Yongxin+Guo%2C+Mohammed+Bennamoun%2C+Farid+Boussaid%2C+Girish+Dwivedi%2C+Luqi+Gong%2C+and+Qiuhong+Ke%2E+2025k%2E+Watch+and+listen%3A+Understanding+audio%2Dvisual%2Dspeech+moments+with+multimodal+llm)
107. Jiajun Li, Yue Ma, Xinyu Zhang, Qingyan Wei, Songhua Liu, and Linfeng Zhang. 2025d. Skipvar: Accelerating visual autoregressive modeling via adaptive frequency-aware skipping. arXiv preprint arXiv:2506.08908. — [arXiv:2506.08908](https://arxiv.org/abs/2506.08908) [find](https://scholar.google.com/scholar?q=Jiajun+Li%2C+Yue+Ma%2C+Xinyu+Zhang%2C+Qingyan+Wei%2C+Songhua+Liu%2C+and+Linfeng+Zhang%2E+2025d%2E+Skipvar%3A+Accelerating+visual+autoregressive+modeling+via+adaptive+frequency%2Daware+skipping%2E+arXiv+preprint+arXiv%3A250)
108. Mengqi Liao, Lu Wang, Chaoyun Zhang, Zekai Shen, Xiaowei Mao, Si Qin, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Huaiyu Wan. 2025. G-KV: Decoding-time KV cache eviction with global attention. arXiv preprint arXiv:2512.00504. — [arXiv:2512.00504](https://arxiv.org/abs/2512.00504) [find](https://scholar.google.com/scholar?q=Mengqi+Liao%2C+Lu+Wang%2C+Chaoyun+Zhang%2C+Zekai+Shen%2C+Xiaowei+Mao%2C+Si+Qin%2C+Qingwei+Lin%2C+Saravan+Rajmohan%2C+Dongmei+Zhang%2C+and+Huaiyu+Wan%2E+2025%2E+G%2DKV%3A+Decoding%2Dtime+KV+cache+eviction+with+global+attention%2E+a)
109. Junyan Lin, Junlong Tong, Hao Wu, Jialiang Zhang, Jinming Liu, Xin Jin, and Xiaoyu Shen. 2026. Speak while watching: Unleashing true real-time video understanding capability of multimodal large language models. arXiv preprint arXiv:2601.06843. — [arXiv:2601.06843](https://arxiv.org/abs/2601.06843) [find](https://scholar.google.com/scholar?q=Junyan+Lin%2C+Junlong+Tong%2C+Hao+Wu%2C+Jialiang+Zhang%2C+Jinming+Liu%2C+Xin+Jin%2C+and+Xiaoyu+Shen%2E+2026%2E+Speak+while+watching%3A+Unleashing+true+real%2Dtime+video+understanding+capability+of+multimodal+large+langua)
110. Zijian Lin, Yang Zhang, Yougen Yuan, Yuming Yan, Jinjiang Liu, Zhiyong Wu, Pengfei Hu, and Qun Yu. 2025. Accelerating autoregressive speech synthesis inference with speech speculative decoding. arXiv preprint arXiv:2505.15380. — [arXiv:2505.15380](https://arxiv.org/abs/2505.15380) [find](https://scholar.google.com/scholar?q=Zijian+Lin%2C+Yang+Zhang%2C+Yougen+Yuan%2C+Yuming+Yan%2C+Jinjiang+Liu%2C+Zhiyong+Wu%2C+Pengfei+Hu%2C+and+Qun+Yu%2E+2025%2E+Accelerating+autoregressive+speech+synthesis+inference+with+speech+speculative+decoding%2E+arXiv+)
111. Aiwei Liu, Minghua He, Shaoxun Zeng, Sijun Zhang, Linhao Zhang, Chuhan Wu, Wei Jia, Yuan Liu, Xiao Zhou, and Jie Zhou. 2025a. Wedlm: Reconciling diffusion language models with standard causal attention for fast inference. arXiv preprint arXiv:2512.22737. — [arXiv:2512.22737](https://arxiv.org/abs/2512.22737) [find](https://scholar.google.com/scholar?q=Aiwei+Liu%2C+Minghua+He%2C+Shaoxun+Zeng%2C+Sijun+Zhang%2C+Linhao+Zhang%2C+Chuhan+Wu%2C+Wei+Jia%2C+Yuan+Liu%2C+Xiao+Zhou%2C+and+Jie+Zhou%2E+2025a%2E+Wedlm%3A+Reconciling+diffusion+language+models+with+standard+causal+attentio)
112. Jiahao Liu, Qifan Wang, Jingang Wang, and Xunliang Cai. 2024a. Speculative decoding via early-exiting for faster llm inference with thompson sampling control mechanism. arXiv preprint arXiv:2406.03853. [find](https://scholar.google.com/scholar?q=Jiahao+Liu%2C+Qifan+Wang%2C+Jingang+Wang%2C+and+Xunliang+Cai%2E+2024a%2E+Speculative+decoding+via+early%2Dexiting+for+faster+llm+inference+with+thompson+sampling+control+mechanism%2E+arXiv+preprint+arXiv%3A2406%2E03853)
113. Jiaheng Liu, Dawei Zhu, Zhiqi Bai, Yancheng He, Huanxuan Liao, Haoran Que, Zekun Wang, Chenchen Zhang, Ge Zhang, Jiebin Zhang, et al. 2025b. [A comprehensive survey on long context language modeling](https://md.research.elamur.ai/free/en/papers/liu-2025-comprehensive-survey-long-context-language/). arXiv preprint arXiv:2503.17407.
114. Jiesong Liu, Brian Park, and Xipeng Shen. 2025c. A drop-in solution for on-the-fly adaptation of speculative decoding in large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9778–9794. [find](https://scholar.google.com/scholar?q=Jiesong+Liu%2C+Brian+Park%2C+and+Xipeng+Shen%2E+2025c%2E+A+drop%2Din+solution+for+on%2Dthe%2Dfly+adaptation+of+speculative+decoding+in+large+language+models%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Associa)
115. Jihao Liu, Zhiding Yu, Shiyi Lan, Shihao Wang, Rongyao Fang, Jan Kautz, Hongsheng Li, and Jose M Alvare. 2024b. Streamchat: Chatting with streaming video. arXiv preprint arXiv:2412.08646. — [arXiv:2412.08646](https://arxiv.org/abs/2412.08646) [find](https://scholar.google.com/scholar?q=Jihao+Liu%2C+Zhiding+Yu%2C+Shiyi+Lan%2C+Shihao+Wang%2C+Rongyao+Fang%2C+Jan+Kautz%2C+Hongsheng+Li%2C+and+Jose+M+Alvare%2E+2024b%2E+Streamchat%3A+Chatting+with+streaming+video%2E+arXiv+preprint+arXiv%3A2412%2E08646%2E+%E2%80%94+%5BarXiv%3A241)
116. Shang Liu, Yao Lu, Wenji Fang, Jing Wang, and Zhiyao Xie. 2025d. Sync-llm: Generation of large-scale synthetic circuit code with hierarchical language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 17361–17376. [find](https://scholar.google.com/scholar?q=Shang+Liu%2C+Yao+Lu%2C+Wenji+Fang%2C+Jing+Wang%2C+and+Zhiyao+Xie%2E+2025d%2E+Sync%2Dllm%3A+Generation+of+large%2Dscale+synthetic+circuit+code+with+hierarchical+language+models%2E+In+Proceedings+of+the+2025+Conference+on+)
117. Tianqiao Liu, Xueyi Li, Hao Wang, Haoxuan Li, Zhichao Chen, Weiqi Luo, and Zitao Liu. 2025e. From text to talk: Audio-language model needs non-autoregressive joint training. arXiv preprint arXiv:2509.20072. — [arXiv:2509.20072](https://arxiv.org/abs/2509.20072) [find](https://scholar.google.com/scholar?q=Tianqiao+Liu%2C+Xueyi+Li%2C+Hao+Wang%2C+Haoxuan+Li%2C+Zhichao+Chen%2C+Weiqi+Luo%2C+and+Zitao+Liu%2E+2025e%2E+From+text+to+talk%3A+Audio%2Dlanguage+model+needs+non%2Dautoregressive+joint+training%2E+arXiv+preprint+arXiv%3A2509%2E)
118. Wenrui Liu, Qian Chen, Wen Wang, Guanrou Yang, Weiqin Li, Minghui Fang, Jialong Zuo, Xiaoda Yang, Tao Jin, Jin Xu, et al. 2025f. Speech token prediction via compressed-to-fine language modeling for speech generation. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 10632–… [find](https://scholar.google.com/scholar?q=Wenrui+Liu%2C+Qian+Chen%2C+Wen+Wang%2C+Guanrou+Yang%2C+Weiqin+Li%2C+Minghui+Fang%2C+Jialong+Zuo%2C+Xiaoda+Yang%2C+Tao+Jin%2C+Jin+Xu%2C+et+al%2E+2025f%2E+Speech+token+prediction+via+compressed%2Dto%2Dfine+language+modeling+for+sp)
119. Xiang Liu, Zhenheng Tang, Peijie Dong, Zeyu Li, Yue Liu, Bo Li, Xuming Hu, and Xiaowen Chu. 2025g. [find](https://scholar.google.com/scholar?q=Xiang+Liu%2C+Zhenheng+Tang%2C+Peijie+Dong%2C+Zeyu+Li%2C+Yue+Liu%2C+Bo+Li%2C+Xuming+Hu%2C+and+Xiaowen+Chu%2E+2025g%2E)
120. Chunkkv: Semantic-preserving kv cache compression for efficient long-context llm inference. arXiv preprint arXiv:2502.00299. [find](https://scholar.google.com/scholar?q=Chunkkv%3A+Semantic%2Dpreserving+kv+cache+compression+for+efficient+long%2Dcontext+llm+inference%2E+arXiv+preprint+arXiv%3A2502%2E00299%2E)
121. Yiheng Liu, Liao Qu, Huichao Zhang, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Xian Li, Shuai Wang, Daniel K Du, et al. 2025h. Detailflow: 1d coarse-to-fine autoregressive image generation via next-detail prediction. arXiv preprint arXiv:2505.21473. — [arXiv:2505.21473](https://arxiv.org/abs/2505.21473) [find](https://scholar.google.com/scholar?q=Yiheng+Liu%2C+Liao+Qu%2C+Huichao+Zhang%2C+Xu+Wang%2C+Yi+Jiang%2C+Yiming+Gao%2C+Hu+Ye%2C+Xian+Li%2C+Shuai+Wang%2C+Daniel+K+Du%2C+et+al%2E+2025h%2E+Detailflow%3A+1d+coarse%2Dto%2Dfine+autoregressive+image+generation+via+next%2Ddetail+)
122. Yuxuan Liu et al. 2024c. [Kivi: A tuning-free asymmetric 2-bit quantization for KV cache](https://md.research.elamur.ai/free/en/papers/liu-2024-kivi-tuning-free-asymmetric-2bit/). arXiv preprint arXiv:2402.02750.
123. Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, and Anshumali Shrivastava. 2023. Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time. Advances in Neural Information Processing Systems, 36:5… [find](https://scholar.google.com/scholar?q=Zichang+Liu%2C+Aditya+Desai%2C+Fangshuo+Liao%2C+Weitao+Wang%2C+Victor+Xie%2C+Zhaozhuo+Xu%2C+Anastasios+Kyrillidis%2C+and+Anshumali+Shrivastava%2E+2023%2E+Scissorhands%3A+Exploiting+the+persistence+of+importance+hypothesi)
124. Yen-Ju Lu, Yashesh Gaur, Wei Zhou, Benjamin Muller, Jesus Villalba, Najim Dehak, Luke Zettlemoyer, Gargi Ghosh, Mike Lewis, Srinivasan Iyer, et al. 2025. Latent speech-text transformer. arXiv preprint arXiv:2510.06195. [find](https://scholar.google.com/scholar?q=Yen%2DJu+Lu%2C+Yashesh+Gaur%2C+Wei+Zhou%2C+Benjamin+Muller%2C+Jesus+Villalba%2C+Najim+Dehak%2C+Luke+Zettlemoyer%2C+Gargi+Ghosh%2C+Mike+Lewis%2C+Srinivasan+Iyer%2C+et+al%2E+2025%2E+Latent+speech%2Dtext+transformer%2E+arXiv+preprint)
125. Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, et al. 2019. [Stacl: Simultaneous translation with implicit anticipation and controllable latency using prefix-to-prefix framework](https://md.research.elamur.ai/free/en/papers/ma-2019-stacl-simultaneous-translation-implicit-anticipation/). In Proceedings of the 57th Annual Meeting…
126. Dominik Macháček, Raj Dabre, and Ondřej Bojar. 2023. Turning whisper into real-time transcription system. arXiv preprint arXiv:2307.14743. [find](https://scholar.google.com/scholar?q=Dominik+Mach%C3%A1c%CC%8Cek%2C+Raj+Dabre%2C+and+Ondr%CC%8Cej+Bojar%2E+2023%2E+Turning+whisper+into+real%2Dtime+transcription+system%2E+arXiv+preprint+arXiv%3A2307%2E14743%2E)
127. Benjamin Minixhofer, Jonas Pfeiffer, and Ivan Vulić. 2023. Where’s the point? self-supervised multilingual punctuation-agnostic sentence segmentation. arXiv preprint arXiv:2305.18893. [find](https://scholar.google.com/scholar?q=Benjamin+Minixhofer%2C+Jonas+Pfeiffer%2C+and+Ivan+Vulic%CC%81%2E+2023%2E+Where%E2%80%99s+the+point%3F+self%2Dsupervised+multilingual+punctuation%2Dagnostic+sentence+segmentation%2E+arXiv+preprint+arXiv%3A2305%2E18893%2E)
128. Tan Dat Nguyen, Ji-Hoon Kim, Jeongsoo Choi, Shukjae Choi, Jinseok Park, Younglo Lee, and Joon Son Chung. 2025. Accelerating codec-based speech synthesis with multi-token prediction and speculative decoding. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing… [find](https://scholar.google.com/scholar?q=Tan+Dat+Nguyen%2C+Ji%2DHoon+Kim%2C+Jeongsoo+Choi%2C+Shukjae+Choi%2C+Jinseok+Park%2C+Younglo+Lee%2C+and+Joon+Son+Chung%2E+2025%2E+Accelerating+codec%2Dbased+speech+synthesis+with+multi%2Dtoken+prediction+and+speculative+dec)
129. Shen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang, Jingyang Ou, Jun Hu, Jun Zhou, Yankai Lin, Ji-Rong Wen, and Chongxuan Li. 2025. [Large language diffusion models](https://md.research.elamur.ai/free/en/papers/nie-2025-large-language-diffusion-models/). arXiv preprint arXiv:2502.09992.
130. Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, and Yu Wang. 2023. Skeleton-of-thought: Large language models can do parallel decoding. Proceedings ENLSP-III. [find](https://scholar.google.com/scholar?q=Xuefei+Ning%2C+Zinan+Lin%2C+Zixuan+Zhou%2C+Zifu+Wang%2C+Huazhong+Yang%2C+and+Yu+Wang%2E+2023%2E+Skeleton%2Dof%2Dthought%3A+Large+language+models+can+do+parallel+decoding%2E+Proceedings+ENLSP%2DIII%2E)
131. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
132. Siqi Ouyang, Xi Xu, and Lei Li. 2025. Infinisst: Simultaneous translation of unbounded speech with large language model. In Findings of the Association for Computational Linguistics: ACL 2025, pages 3032–3046. [find](https://scholar.google.com/scholar?q=Siqi+Ouyang%2C+Xi+Xu%2C+and+Lei+Li%2E+2025%2E+Infinisst%3A+Simultaneous+translation+of+unbounded+speech+with+large+language+model%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2025%2C+pages+3)
133. Sunny Panchal, Apratim Bhattacharyya, Guillaume Berger, Antoine Mercier, Cornelius Böhm, Florian Dietrichkeit, Reza Pourreza, Xuanlin Li, Pulkit Madan, Mingu Lee, et al. 2024. What to say and when to say it: Live fitness coaching as a testbed for situated interaction. Advances in Neural Information… [find](https://scholar.google.com/scholar?q=Sunny+Panchal%2C+Apratim+Bhattacharyya%2C+Guillaume+Berger%2C+Antoine+Mercier%2C+Cornelius+B%C3%B6hm%2C+Florian+Dietrichkeit%2C+Reza+Pourreza%2C+Xuanlin+Li%2C+Pulkit+Madan%2C+Mingu+Lee%2C+et+al%2E+2024%2E+What+to+say+and+when+to+)
134. William Peebles and Saining Xie. 2022. [Scalable diffusion models with transformers](https://md.research.elamur.ai/free/en/papers/peebles-2022-scalable-diffusion-models-transformers/). arXiv preprint arXiv:2212.09748.
135. Rui Qian, Shuangrui Ding, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Dahua Lin, and Jiaqi Wang. 2025. Dispider: Enabling video llms with active real-time interaction via disentangled perception, decision, and reaction. In Proceedings of the Computer Vision and Pattern Recognition Conference, p… [find](https://scholar.google.com/scholar?q=Rui+Qian%2C+Shuangrui+Ding%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Yuhang+Zang%2C+Yuhang+Cao%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2025%2E+Dispider%3A+Enabling+video+llms+with+active+real%2Dtime+interaction+via+disentangled+perception%2C)
136. Rui Qian, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Shuangrui Ding, Dahua Lin, and Jiaqi Wang. 2024. Streaming long video understanding with large language models. Advances in Neural Information Processing Systems, 37:119336–119360. [find](https://scholar.google.com/scholar?q=Rui+Qian%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Yuhang+Zang%2C+Shuangrui+Ding%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2024%2E+Streaming+long+video+understanding+with+large+language+models%2E+Advances+in+Neural+Information+Processing)
137. Zhen Qin, Weigao Sun, Dong Li, Xuyang Shen, Weixuan Sun, and Yiran Zhong. 2024. [Lightning attention-2: A free lunch for handling unlimited sequence lengths in large language models](https://md.research.elamur.ai/free/en/papers/qin-2024-lightning-attention-2-free/). arXiv preprint arXiv:2401.04658.
138. Ziran Qin, Yuchen Cao, Mingbao Lin, Wen Hu, Shixuan Fan, Ke Cheng, Weiyao Lin, and Jianguo Li. 2025a. Cake: Cascading and adaptive kv cache eviction with layer preferences. arXiv preprint arXiv:2503.12491. — [arXiv:2503.12491](https://arxiv.org/abs/2503.12491) [find](https://scholar.google.com/scholar?q=Ziran+Qin%2C+Yuchen+Cao%2C+Mingbao+Lin%2C+Wen+Hu%2C+Shixuan+Fan%2C+Ke+Cheng%2C+Weiyao+Lin%2C+and+Jianguo+Li%2E+2025a%2E+Cake%3A+Cascading+and+adaptive+kv+cache+eviction+with+layer+preferences%2E+arXiv+preprint+arXiv%3A2503%2E1)
139. Ziran Qin, Youru Lv, Mingbao Lin, Zeren Zhang, Chan-fan Gan, Tieyuan Chen, and Weiyao Lin. 2025b. Autoregressive image generation needs only a few lines of cached tokens. arXiv preprint arXiv:2512.04857. — [arXiv:2512.04857](https://arxiv.org/abs/2512.04857) [find](https://scholar.google.com/scholar?q=Ziran+Qin%2C+Youru+Lv%2C+Mingbao+Lin%2C+Zeren+Zhang%2C+Chan%2Dfan+Gan%2C+Tieyuan+Chen%2C+and+Weiyao+Lin%2E+2025b%2E+Autoregressive+image+generation+needs+only+a+few+lines+of+cached+tokens%2E+arXiv+preprint+arXiv%3A2512%2E048)
140. Ziran Qin, Youru Lv, Mingbao Lin, Zeren Zhang, Danping Zou, and Weiyao Lin. 2025c. Head-aware kv cache compression for efficient visual autoregressive modeling. arXiv preprint arXiv:2504.09261. — [arXiv:2504.09261](https://arxiv.org/abs/2504.09261) [find](https://scholar.google.com/scholar?q=Ziran+Qin%2C+Youru+Lv%2C+Mingbao+Lin%2C+Zeren+Zhang%2C+Danping+Zou%2C+and+Weiyao+Lin%2E+2025c%2E+Head%2Daware+kv+cache+compression+for+efficient+visual+autoregressive+modeling%2E+arXiv+preprint+arXiv%3A2504%2E09261%2E+%E2%80%94+%5BarX)
141. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8763. Pm…
142. Matthew Raffel, Victor Agostinelli, and Lizhong Chen. 2024. Simultaneous masking, not prompting optimization: A paradigm shift in fine-tuning llms for simultaneous translation. arXiv preprint arXiv:2405.10443. [find](https://scholar.google.com/scholar?q=Matthew+Raffel%2C+Victor+Agostinelli%2C+and+Lizhong+Chen%2E+2024%2E+Simultaneous+masking%2C+not+prompting+optimization%3A+A+paradigm+shift+in+fine%2Dtuning+llms+for+simultaneous+translation%2E+arXiv+preprint+arXiv%3A24)
143. Aditya Ramesh et al. 2021. [Zero-shot text-to-image generation](https://md.research.elamur.ai/free/en/papers/ramesh-2021-zero-shot-text-image-generation/). arXiv preprint arXiv:2102.12092.
144. Shuhuai Ren, Shuming Ma, Xu Sun, and Furu Wei. 2025. Next block prediction: Video generation via semi-autoregressive modeling. arXiv preprint arXiv:2502.07737. — [arXiv:2502.07737](https://arxiv.org/abs/2502.07737) [find](https://scholar.google.com/scholar?q=Shuhuai+Ren%2C+Shuming+Ma%2C+Xu+Sun%2C+and+Furu+Wei%2E+2025%2E+Next+block+prediction%3A+Video+generation+via+semi%2Dautoregressive+modeling%2E+arXiv+preprint+arXiv%3A2502%2E07737%2E+%E2%80%94+%5BarXiv%3A2502%2E07737%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
145. Paul K Rubenstein, Chulayuth Asawaroengchai, Duc Dung Nguyen, Ankur Bapna, Zalán Borsos, Félix de Chaumont Quitry, Peter Chen, Dalia El Badawy, Wei Han, Eugene Kharitonov, et al. 2023. [Audiopalm: A large language model that can speak and listen](https://md.research.elamur.ai/free/en/papers/rubenstein-2023-audiopalm-large-language-model-that/). arXiv preprint arXiv:2306.12925.
146. Laura Ruis, Mitchell Stern, Julia Proskurnia, and William Chan. 2020. Insertion-deletion transformer. arXiv preprint arXiv:2001.05540. — [arXiv:2001.05540](https://arxiv.org/abs/2001.05540) [find](https://scholar.google.com/scholar?q=Laura+Ruis%2C+Mitchell+Stern%2C+Julia+Proskurnia%2C+and+William+Chan%2E+2020%2E+Insertion%2Ddeletion+transformer%2E+arXiv+preprint+arXiv%3A2001%2E05540%2E+%E2%80%94+%5BarXiv%3A2001%2E05540%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2001%2E05540%29)
147. Frank Seide, Morrie Doulaty, Yangyang Shi, Yashesh Gaur, Junteng Jia, and Chunyang Wu. 2024. Speech reallm–real-time streaming speech recognition with multimodal llms by teaching the flow of time. arXiv preprint arXiv:2406.09569. — [arXiv:2406.09569](https://arxiv.org/abs/2406.09569) [find](https://scholar.google.com/scholar?q=Frank+Seide%2C+Morrie+Doulaty%2C+Yangyang+Shi%2C+Yashesh+Gaur%2C+Junteng+Jia%2C+and+Chunyang+Wu%2E+2024%2E+Speech+reallm%E2%80%93real%2Dtime+streaming+speech+recognition+with+multimodal+llms+by+teaching+the+flow+of+time%2E+arX)
148. Zhengyan Sheng, Zhihao Du, Shiliang Zhang, Zhijie Yan, Yexin Yang, and Zhenhua Ling. 2025. Syncspeech: Low-latency and efficient dual-stream text-to-speech based on temporal masked transformer. arXiv preprint arXiv:2502.11094. — [arXiv:2502.11094](https://arxiv.org/abs/2502.11094) [find](https://scholar.google.com/scholar?q=Zhengyan+Sheng%2C+Zhihao+Du%2C+Shiliang+Zhang%2C+Zhijie+Yan%2C+Yexin+Yang%2C+and+Zhenhua+Ling%2E+2025%2E+Syncspeech%3A+Low%2Dlatency+and+efficient+dual%2Dstream+text%2Dto%2Dspeech+based+on+temporal+masked+transformer%2E+arXiv+)
149. Mohan Shi, Yuchun Shu, Lingyun Zuo, Qian Chen, Shiliang Zhang, Jie Zhang, and Li-Rong Dai. 2023. Semantic vad: Low-latency voice activity detection for speech interaction. arXiv preprint arXiv:2305.12450. — [arXiv:2305.12450](https://arxiv.org/abs/2305.12450) [find](https://scholar.google.com/scholar?q=Mohan+Shi%2C+Yuchun+Shu%2C+Lingyun+Zuo%2C+Qian+Chen%2C+Shiliang+Zhang%2C+Jie+Zhang%2C+and+Li%2DRong+Dai%2E+2023%2E+Semantic+vad%3A+Low%2Dlatency+voice+activity+detection+for+speech+interaction%2E+arXiv+preprint+arXiv%3A2305%2E12)
150. Sambal Shikhar, Mohammed Irfan Kurpath, Sahal Shaji Mullappilly, Jean Lahoud, Fahad Shahbaz Khan, Rao Muhammad Anwer, Salman Khan, and Hisham Cholakkal. 2025. Llmvox: Autoregressive streaming text-to-speech model for any llm. In Findings of the Association for Computational Linguistics: ACL 2025, pa… [find](https://scholar.google.com/scholar?q=Sambal+Shikhar%2C+Mohammed+Irfan+Kurpath%2C+Sahal+Shaji+Mullappilly%2C+Jean+Lahoud%2C+Fahad+Shahbaz+Khan%2C+Rao+Muhammad+Anwer%2C+Salman+Khan%2C+and+Hisham+Cholakkal%2E+2025%2E+Llmvox%3A+Autoregressive+streaming+text%2Dto%2D)
151. Junhyuk So, Juncheol Shin, Hyunho Kook, and Eunhyeok Park. 2025. Grouped speculative decoding for autoregressive image generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 15375–15384. [find](https://scholar.google.com/scholar?q=Junhyuk+So%2C+Juncheol+Shin%2C+Hyunho+Kook%2C+and+Eunhyeok+Park%2E+2025%2E+Grouped+speculative+decoding+for+autoregressive+image+generation%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conference+on+Computer+V)
152. Yuxuan Song, Zheng Zhang, Cheng Luo, Pengyang Gao, Fan Xia, Hao Luo, Zheng Li, Yuehang Yang, Hongli Yu, Xingwei Qu, et al. 2025. [Seed diffusion: A large-scale diffusion language model with high-speed inference](https://md.research.elamur.ai/free/en/papers/song-2025-seed-diffusion-large-scale/). arXiv preprint arXiv:2508.02193.
153. Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, and Zehuan Yuan. 2024. Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525. — [arXiv:2406.06525](https://arxiv.org/abs/2406.06525) [find](https://scholar.google.com/scholar?q=Peize+Sun%2C+Yi+Jiang%2C+Shoufa+Chen%2C+Shilong+Zhang%2C+Bingyue+Peng%2C+Ping+Luo%2C+and+Zehuan+Yuan%2E+2024%2E+Autoregressive+model+beats+diffusion%3A+Llama+for+scalable+image+generation%2E+arXiv+preprint+arXiv%3A2406%2E065)
154. Hanlin Tang, Yang Lin, Jing Lin, Qingsen Han, Shikuan Hong, Yiwu Yao, and Gongyi Wang. 2024. Razorattention: Efficient kv cache compression through retrieval heads. arXiv preprint arXiv:2407.15891. — [arXiv:2407.15891](https://arxiv.org/abs/2407.15891) [find](https://scholar.google.com/scholar?q=Hanlin+Tang%2C+Yang+Lin%2C+Jing+Lin%2C+Qingsen+Han%2C+Shikuan+Hong%2C+Yiwu+Yao%2C+and+Gongyi+Wang%2E+2024%2E+Razorattention%3A+Efficient+kv+cache+compression+through+retrieval+heads%2E+arXiv+preprint+arXiv%3A2407%2E15891%2E+%E2%80%94+)
155. Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang. 2025. Dycoke: Dynamic compression of tokens for fast video large language models. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 18992–19001. [find](https://scholar.google.com/scholar?q=Keda+Tao%2C+Can+Qin%2C+Haoxuan+You%2C+Yang+Sui%2C+and+Huan+Wang%2E+2025%2E+Dycoke%3A+Dynamic+compression+of+tokens+for+fast+video+large+language+models%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition)
156. Chameleon Team. 2024. [Chameleon: Mixed-modal early-fusion foundation models](https://md.research.elamur.ai/free/en/papers/team-2024-chameleon-mixed-modal-early-fusion/). arXiv preprint arXiv:2405.09818.
157. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al. 2023. [Gemini: a family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805.
158. Yao Teng, Han Shi, Xian Liu, Xuefei Ning, Guohao Dai, Yu Wang, Zhenguo Li, and Xihui Liu. 2024. Accelerating auto-regressive text-to-image generation with training-free speculative jacobi decoding. arXiv preprint arXiv:2410.01699. — [arXiv:2410.01699](https://arxiv.org/abs/2410.01699) [find](https://scholar.google.com/scholar?q=Yao+Teng%2C+Han+Shi%2C+Xian+Liu%2C+Xuefei+Ning%2C+Guohao+Dai%2C+Yu+Wang%2C+Zhenguo+Li%2C+and+Xihui+Liu%2E+2024%2E+Accelerating+auto%2Dregressive+text%2Dto%2Dimage+generation+with+training%2Dfree+speculative+jacobi+decoding%2E+ar)
159. Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, and Liwei Wang. 2024. Visual autoregressive modeling: Scalable image generation via next-scale prediction. Advances in neural information processing systems, 37:84839–84865. [find](https://scholar.google.com/scholar?q=Keyu+Tian%2C+Yi+Jiang%2C+Zehuan+Yuan%2C+Bingyue+Peng%2C+and+Liwei+Wang%2E+2024%2E+Visual+autoregressive+modeling%3A+Scalable+image+generation+via+next%2Dscale+prediction%2E+Advances+in+neural+information+processing+sys)
160. Yuchuan Tian, Yuchen Liang, Jiacheng Sun, Shuo Zhang, Guangwen Yang, Yingte Shu, Sibo Fang, Tianyu Guo, Kai Han, Chao Xu, et al. 2025. From next-token to next-block: A principled adaptation path for diffusion llms. arXiv preprint arXiv:2512.06776. — [arXiv:2512.06776](https://arxiv.org/abs/2512.06776) [find](https://scholar.google.com/scholar?q=Yuchuan+Tian%2C+Yuchen+Liang%2C+Jiacheng+Sun%2C+Shuo+Zhang%2C+Guangwen+Yang%2C+Yingte+Shu%2C+Sibo+Fang%2C+Tianyu+Guo%2C+Kai+Han%2C+Chao+Xu%2C+et+al%2E+2025%2E+From+next%2Dtoken+to+next%2Dblock%3A+A+principled+adaptation+path+for+d)
161. Junlong Tong, Yingqi Fan, Anhao Zhao, Yunpu Ma, and Xiaoyu Shen. 2025a. Streamingthinker: Large language models can think while reading. arXiv preprint arXiv:2510.17238. — [arXiv:2510.17238](https://arxiv.org/abs/2510.17238) [find](https://scholar.google.com/scholar?q=Junlong+Tong%2C+Yingqi+Fan%2C+Anhao+Zhao%2C+Yunpu+Ma%2C+and+Xiaoyu+Shen%2E+2025a%2E+Streamingthinker%3A+Large+language+models+can+think+while+reading%2E+arXiv+preprint+arXiv%3A2510%2E17238%2E+%E2%80%94+%5BarXiv%3A2510%2E17238%5D%28https%3A%2F%2Fa)
162. Junlong Tong, Jinlan Fu, Zixuan Lin, Yingqi Fan, Anhao Zhao, Hui Su, and Xiaoyu Shen. 2025b. Llm as effective streaming processor: Bridging streaming-batch mismatches with group position encoding. arXiv preprint arXiv:2505.16983. [find](https://scholar.google.com/scholar?q=Junlong+Tong%2C+Jinlan+Fu%2C+Zixuan+Lin%2C+Yingqi+Fan%2C+Anhao+Zhao%2C+Hui+Su%2C+and+Xiaoyu+Shen%2E+2025b%2E+Llm+as+effective+streaming+processor%3A+Bridging+streaming%2Dbatch+mismatches+with+group+position+encoding%2E+arX)
163. Genshun Wan, Wenhui Zhang, Jing-Xuan Zhang, Shifu Xiong, Jianqing Gao, and Zhongfu Ye. 2026. Streaming speech recognition with decoder-only large language models and latency optimization. arXiv preprint arXiv:2601.22779. — [arXiv:2601.22779](https://arxiv.org/abs/2601.22779) [find](https://scholar.google.com/scholar?q=Genshun+Wan%2C+Wenhui+Zhang%2C+Jing%2DXuan+Zhang%2C+Shifu+Xiong%2C+Jianqing+Gao%2C+and+Zhongfu+Ye%2E+2026%2E+Streaming+speech+recognition+with+decoder%2Donly+large+language+models+and+latency+optimization%2E+arXiv+prepri)
164. Ao Wang, Hui Chen, Jiaxin Li, Jianchao Tan, Kefeng Zhang, Xunliang Cai, Zijia Lin, Jungong Han, and Guiguang Ding. 2024a. Prefixkv: Adaptive prefix kv cache is what vision instruction-following models need for efficient generation. arXiv preprint arXiv:2412.03409. — [arXiv:2412.03409](https://arxiv.org/abs/2412.03409) [find](https://scholar.google.com/scholar?q=Ao+Wang%2C+Hui+Chen%2C+Jiaxin+Li%2C+Jianchao+Tan%2C+Kefeng+Zhang%2C+Xunliang+Cai%2C+Zijia+Lin%2C+Jungong+Han%2C+and+Guiguang+Ding%2E+2024a%2E+Prefixkv%3A+Adaptive+prefix+kv+cache+is+what+vision+instruction%2Dfollowing+models)
165. Chunqi Wang, Ji Zhang, Haiqing Chen, Chenghao Tao, et al. 2018. Semi-autoregressive neural machine translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP). ArXiv:1808.08583. [find](https://scholar.google.com/scholar?q=Chunqi+Wang%2C+Ji+Zhang%2C+Haiqing+Chen%2C+Chenghao+Tao%2C+et+al%2E+2018%2E+Semi%2Dautoregressive+neural+machine+translation%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+Language+Processin)
166. Haibo Wang, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge, Afshin Dehghan, Meng Cao, and Ping Huang. 2025a. Streambridge: Turning your offline video large language model into a proactive streaming assistant. arXiv preprint arXiv:2505.05467. — [arXiv:2505.05467](https://arxiv.org/abs/2505.05467) [find](https://scholar.google.com/scholar?q=Haibo+Wang%2C+Bo+Feng%2C+Zhengfeng+Lai%2C+Mingze+Xu%2C+Shiyu+Li%2C+Weifeng+Ge%2C+Afshin+Dehghan%2C+Meng+Cao%2C+and+Ping+Huang%2E+2025a%2E+Streambridge%3A+Turning+your+offline+video+large+language+model+into+a+proactive+str)
167. Haoyu Wang, Guoqiang Hu, Guodong Lin, Wei-Qiang Zhang, and Jian Li. 2024b. Simul-whisper: Attention-guided streaming whisper with truncation detection. arXiv preprint arXiv:2406.10052. — [arXiv:2406.10052](https://arxiv.org/abs/2406.10052) [find](https://scholar.google.com/scholar?q=Haoyu+Wang%2C+Guoqiang+Hu%2C+Guodong+Lin%2C+Wei%2DQiang+Zhang%2C+and+Jian+Li%2E+2024b%2E+Simul%2Dwhisper%3A+Attention%2Dguided+streaming+whisper+with+truncation+detection%2E+arXiv+preprint+arXiv%3A2406%2E10052%2E+%E2%80%94+%5BarXiv%3A2406%2E1)
168. Minghan Wang, Thuy Vu, Jinming Zhao, Fatemeh Shiri, Ehsan Shareghi, and Gholamreza Haffari. 2024c. Simultaneous machine translation with large language models. In Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association, pages 89–103. [find](https://scholar.google.com/scholar?q=Minghan+Wang%2C+Thuy+Vu%2C+Jinming+Zhao%2C+Fatemeh+Shiri%2C+Ehsan+Shareghi%2C+and+Gholamreza+Haffari%2E+2024c%2E+Simultaneous+machine+translation+with+large+language+models%2E+In+Proceedings+of+the+22nd+Annual+Worksh)
169. Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, and Furu Wei. 2023. Augmenting language models with long-term memory. Advances in Neural Information Processing Systems, 36:74530–74543. [find](https://scholar.google.com/scholar?q=Weizhi+Wang%2C+Li+Dong%2C+Hao+Cheng%2C+Xiaodong+Liu%2C+Xifeng+Yan%2C+Jianfeng+Gao%2C+and+Furu+Wei%2E+2023%2E+Augmenting+language+models+with+long%2Dterm+memory%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A745)
170. Xindi Wang, Mahsa Salmani, Parsa Omidi, Xiangyu Ren, Mehdi Rezagholizadeh, and Armaghan Eshaghi. 2024d. [Beyond the limits: A survey of techniques to extend the context length in large language models](https://md.research.elamur.ai/free/en/papers/wang-2024-limits-survey-techniques-extend-context/). arXiv preprint arXiv:2402.02244.
171. Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Zhen Li, Qiying Yu, et al. 2024e. Emu3: Next-token prediction is all you need. arXiv preprint arXiv:2409.18869. — [arXiv:2409.18869](https://arxiv.org/abs/2409.18869) [find](https://scholar.google.com/scholar?q=Xinlong+Wang%2C+Xiaosong+Zhang%2C+Zhengxiong+Luo%2C+Quan+Sun%2C+Yufeng+Cui%2C+Jinsheng+Wang%2C+Fan+Zhang%2C+Yueze+Wang%2C+Zhen+Li%2C+Qiying+Yu%2C+et+al%2E+2024e%2E+Emu3%3A+Next%2Dtoken+prediction+is+all+you+need%2E+arXiv+preprint+)
172. Yiyu Wang, Xuyang Liu, Xiyan Gui, Xinying Lin, Boxue Yang, Chenfei Liao, Tailai Chen, and Linfeng Zhang. 2025b. Accelerating streaming video large language models via hierarchical token compression. arXiv preprint arXiv:2512.00891. — [arXiv:2512.00891](https://arxiv.org/abs/2512.00891) [find](https://scholar.google.com/scholar?q=Yiyu+Wang%2C+Xuyang+Liu%2C+Xiyan+Gui%2C+Xinying+Lin%2C+Boxue+Yang%2C+Chenfei+Liao%2C+Tailai+Chen%2C+and+Linfeng+Zhang%2E+2025b%2E+Accelerating+streaming+video+large+language+models+via+hierarchical+token+compression%2E+a)
173. Yuancheng Wang, Haoyue Zhan, Liwei Liu, Ruihong Zeng, Haotian Guo, Jiachen Zheng, Qiang Zhang, Xueyao Zhang, Shunsi Zhang, and Zhizheng Wu. 2024f. Maskgct: Zero-shot text-to-speech with masked generative codec transformer. arXiv preprint arXiv:2409.00750. — [arXiv:2409.00750](https://arxiv.org/abs/2409.00750) [find](https://scholar.google.com/scholar?q=Yuancheng+Wang%2C+Haoyue+Zhan%2C+Liwei+Liu%2C+Ruihong+Zeng%2C+Haotian+Guo%2C+Jiachen+Zheng%2C+Qiang+Zhang%2C+Xueyao+Zhang%2C+Shunsi+Zhang%2C+and+Zhizheng+Wu%2E+2024f%2E+Maskgct%3A+Zero%2Dshot+text%2Dto%2Dspeech+with+masked+generat)
174. Yueqian Wang, Songxiang Liu, Disong Wang, Nuo Xu, Guanglu Wan, Huishuai Zhang, and Dongyan Zhao. 2025c. Mmduet2: Enhancing proactive interaction of video mllms with multi-turn reinforcement learning. arXiv preprint arXiv:2512.06810. — [arXiv:2512.06810](https://arxiv.org/abs/2512.06810) [find](https://scholar.google.com/scholar?q=Yueqian+Wang%2C+Songxiang+Liu%2C+Disong+Wang%2C+Nuo+Xu%2C+Guanglu+Wan%2C+Huishuai+Zhang%2C+and+Dongyan+Zhao%2E+2025c%2E+Mmduet2%3A+Enhancing+proactive+interaction+of+video+mllms+with+multi%2Dturn+reinforcement+learning%2E+)
175. Yuhao Wang, Heyang Liu, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, and Yu Wang. 2025d. Vocalnet: Speech llm with multi-token prediction for faster and high-quality generation. arXiv preprint arXiv:2504.04060. — [arXiv:2504.04060](https://arxiv.org/abs/2504.04060) [find](https://scholar.google.com/scholar?q=Yuhao+Wang%2C+Heyang+Liu%2C+Ziyang+Cheng%2C+Ronghua+Wu%2C+Qunshan+Gu%2C+Yanfeng+Wang%2C+and+Yu+Wang%2E+2025d%2E+Vocalnet%3A+Speech+llm+with+multi%2Dtoken+prediction+for+faster+and+high%2Dquality+generation%2E+arXiv+preprint+)
176. Yuqing Wang, Shuhuai Ren, Zhijie Lin, Yujin Han, Haoyuan Guo, Zhenheng Yang, Difan Zou, Jiashi Feng, and Xihui Liu. 2025e. Parallelized autoregressive visual generation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 12955–12965. [find](https://scholar.google.com/scholar?q=Yuqing+Wang%2C+Shuhuai+Ren%2C+Zhijie+Lin%2C+Yujin+Han%2C+Haoyuan+Guo%2C+Zhenheng+Yang%2C+Difan+Zou%2C+Jiashi+Feng%2C+and+Xihui+Liu%2E+2025e%2E+Parallelized+autoregressive+visual+generation%2E+In+Proceedings+of+the+Computer)
177. Yuxuan Wang, Yiqi Song, Cihang Xie, Yang Liu, and Zilong Zheng. 2025f. Videollamb: Long streaming video understanding with recurrent memory bridges. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 24170–24181. [find](https://scholar.google.com/scholar?q=Yuxuan+Wang%2C+Yiqi+Song%2C+Cihang+Xie%2C+Yang+Liu%2C+and+Zilong+Zheng%2E+2025f%2E+Videollamb%3A+Long+streaming+video+understanding+with+recurrent+memory+bridges%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Confer)
178. Jiaer Xia, Peixian Chen, Mengdan Zhang, Xing Sun, and Kaiyang Zhou. 2025a. Streaming video instruction tuning. arXiv preprint arXiv:2512.21334. — [arXiv:2512.21334](https://arxiv.org/abs/2512.21334) [find](https://scholar.google.com/scholar?q=Jiaer+Xia%2C+Peixian+Chen%2C+Mengdan+Zhang%2C+Xing+Sun%2C+and+Kaiyang+Zhou%2E+2025a%2E+Streaming+video+instruction+tuning%2E+arXiv+preprint+arXiv%3A2512%2E21334%2E+%E2%80%94+%5BarXiv%3A2512%2E21334%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2512%2E21334%29)
179. Yinfeng Xia, Huiyan Li, Chenyang Le, Manhong Wang, Yutao Sun, Xingyang Ma, and Yanmin Qian. 2025b. Mfla: Monotonic finite look-ahead attention for streaming speech recognition. arXiv preprint arXiv:2506.03722. — [arXiv:2506.03722](https://arxiv.org/abs/2506.03722) [find](https://scholar.google.com/scholar?q=Yinfeng+Xia%2C+Huiyan+Li%2C+Chenyang+Le%2C+Manhong+Wang%2C+Yutao+Sun%2C+Xingyang+Ma%2C+and+Yanmin+Qian%2E+2025b%2E+Mfla%3A+Monotonic+finite+look%2Dahead+attention+for+streaming+speech+recognition%2E+arXiv+preprint+arXiv%3A25)
180. Zili Wang, Robert Zhang, Kun Ding, Qi Yang, Fei Li, and Shiming Xiang. 2024g. Continuous speculative decoding for autoregressive image generation. arXiv preprint arXiv:2411.11925. — [arXiv:2411.11925](https://arxiv.org/abs/2411.11925) [find](https://scholar.google.com/scholar?q=Zili+Wang%2C+Robert+Zhang%2C+Kun+Ding%2C+Qi+Yang%2C+Fei+Li%2C+and+Shiming+Xiang%2E+2024g%2E+Continuous+speculative+decoding+for+autoregressive+image+generation%2E+arXiv+preprint+arXiv%3A2411%2E11925%2E+%E2%80%94+%5BarXiv%3A2411%2E11925%5D)
181. Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, and Song Han. 2024a. [Duoattention: Efficient long-context llm inference with retrieval and streaming heads](https://md.research.elamur.ai/free/en/papers/xiao-2024-duoattention-efficient-long-context-llm/). arXiv preprint arXiv:2410.10819.
182. Chiyue Wei, Cong Guo, Junyao Zhang, Haoxuan Shan, Yifan Xu, Ziyue Zhang, Yudong Liu, Qinsi Wang, Changchun Zhou, Hai Li, et al. 2025a. Focus: A streaming concentration architecture for efficient vision-language models. arXiv preprint arXiv:2512.14661. — [arXiv:2512.14661](https://arxiv.org/abs/2512.14661) [find](https://scholar.google.com/scholar?q=Chiyue+Wei%2C+Cong+Guo%2C+Junyao+Zhang%2C+Haoxuan+Shan%2C+Yifan+Xu%2C+Ziyue+Zhang%2C+Yudong+Liu%2C+Qinsi+Wang%2C+Changchun+Zhou%2C+Hai+Li%2C+et+al%2E+2025a%2E+Focus%3A+A+streaming+concentration+architecture+for+efficient+visio)
183. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Yuandong+Tian%2C+Beidi+Chen%2C+Song+Han%2C+and+Mike+Lewis%2E+2023%2E+Efficient+streaming+language+models+with+attention+sinks%2E+arXiv+preprint+arXiv%3A2309%2E17453%2E)
184. Meng Wei, Chenyang Wan, Xiqian Yu, Tai Wang, Yuqiang Yang, Xiaohan Mao, Chenming Zhu, Wenzhe Cai, Hanqing Wang, Yilun Chen, et al. 2025b. Streamvln: Streaming vision-and-language navigation via slowfast context modeling. arXiv preprint arXiv:2507.05240. — [arXiv:2507.05240](https://arxiv.org/abs/2507.05240) [find](https://scholar.google.com/scholar?q=Meng+Wei%2C+Chenyang+Wan%2C+Xiqian+Yu%2C+Tai+Wang%2C+Yuqiang+Yang%2C+Xiaohan+Mao%2C+Chenming+Zhu%2C+Wenzhe+Cai%2C+Hanqing+Wang%2C+Yilun+Chen%2C+et+al%2E+2025b%2E+Streamvln%3A+Streaming+vision%2Dand%2Dlanguage+navigation+via+slowfa)
185. Zhuofan Wen, Shangtong Gui, and Yang Feng. 2024. Speculative decoding with ctc-based draft model for llm inference acceleration. Advances in Neural Information Processing Systems, 37:92082–92100. [find](https://scholar.google.com/scholar?q=Zhuofan+Wen%2C+Shangtong+Gui%2C+and+Yang+Feng%2E+2024%2E+Speculative+decoding+with+ctc%2Dbased+draft+model+for+llm+inference+acceleration%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A92082%E2%80%9392100%2E)
186. Haibin Wu, Naoyuki Kanda, Sefik Emre Eskimez, and Jinyu Li. 2024a. Ts3-codec: Transformer-based simple streaming single codec. arXiv preprint arXiv:2411.18803. — [arXiv:2411.18803](https://arxiv.org/abs/2411.18803) [find](https://scholar.google.com/scholar?q=Haibin+Wu%2C+Naoyuki+Kanda%2C+Sefik+Emre+Eskimez%2C+and+Jinyu+Li%2E+2024a%2E+Ts3%2Dcodec%3A+Transformer%2Dbased+simple+streaming+single+codec%2E+arXiv+preprint+arXiv%3A2411%2E18803%2E+%E2%80%94+%5BarXiv%3A2411%2E18803%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
187. Hao Wu, Yingqi Fan, Jinyang Dai, Junlong Tong, Yunpu Ma, and Xiaoyu Shen. 2026a. Hidrop: Hierarchical vision token reduction in mllms via late injection, concave pyramid pruning, and early exit. arXiv preprint arXiv:2602.23699. — [arXiv:2602.23699](https://arxiv.org/abs/2602.23699) [find](https://scholar.google.com/scholar?q=Hao+Wu%2C+Yingqi+Fan%2C+Jinyang+Dai%2C+Junlong+Tong%2C+Yunpu+Ma%2C+and+Xiaoyu+Shen%2E+2026a%2E+Hidrop%3A+Hierarchical+vision+token+reduction+in+mllms+via+late+injection%2C+concave+pyramid+pruning%2C+and+early+exit%2E+arXiv)
188. Hao Wu, Junlong Tong, Xudong Wang, Yang Tan, Changyu Zeng, Anastasia Antsiferova, and Xiaoyu Shen. 2026b. From data to model: A survey of the compression lifecycle in mllms. TechRxiv preprint TechRxiv:177220375.55495124. [find](https://scholar.google.com/scholar?q=Hao+Wu%2C+Junlong+Tong%2C+Xudong+Wang%2C+Yang+Tan%2C+Changyu+Zeng%2C+Anastasia+Antsiferova%2C+and+Xiaoyu+Shen%2E+2026b%2E+From+data+to+model%3A+A+survey+of+the+compression+lifecycle+in+mllms%2E+TechRxiv+preprint+TechRxiv)
189. Shiwei Wu, Joya Chen, Kevin Qinghong Lin, Qimeng Wang, Yan Gao, Qianli Xu, Tong Xu, Yao Hu, Enhong Chen, and Mike Zheng Shou. 2024b. Videollm-mod: Efficient video-language streaming with mixture-of-depths vision computation. Advances in Neural Information Processing Systems, 37:109922–109947. [find](https://scholar.google.com/scholar?q=Shiwei+Wu%2C+Joya+Chen%2C+Kevin+Qinghong+Lin%2C+Qimeng+Wang%2C+Yan+Gao%2C+Qianli+Xu%2C+Tong+Xu%2C+Yao+Hu%2C+Enhong+Chen%2C+and+Mike+Zheng+Shou%2E+2024b%2E+Videollm%2Dmod%3A+Efficient+video%2Dlanguage+streaming+with+mixture%2Dof%2Dde)
190. Yecheng Wu, Han Cai, Junyu Chen, Zhuoyang Zhang, Enze Xie, Jincheng Yu, Junsong Chen, Jinyi Hu, Yao Lu, and Song Han. 2025. Dc-ar: Efficient masked autoregressive image generation with deep compression hybrid tokenizer. In Proceedings of the IEEE/CVF International Conference on Computer Vision, page… [find](https://scholar.google.com/scholar?q=Yecheng+Wu%2C+Han+Cai%2C+Junyu+Chen%2C+Zhuoyang+Zhang%2C+Enze+Xie%2C+Jincheng+Yu%2C+Junsong+Chen%2C+Jinyi+Hu%2C+Yao+Lu%2C+and+Song+Han%2E+2025%2E+Dc%2Dar%3A+Efficient+masked+autoregressive+image+generation+with+deep+compressio)
191. Zilin Xiao, Hongming Zhang, Tao Ge, Siru Ouyang, Vicente Ordonez, and Dong Yu. 2024b. Parallel-spec: Parallel drafter for efficient speculative decoding. arXiv preprint arXiv:2410.05589. — [arXiv:2410.05589](https://arxiv.org/abs/2410.05589) [find](https://scholar.google.com/scholar?q=Zilin+Xiao%2C+Hongming+Zhang%2C+Tao+Ge%2C+Siru+Ouyang%2C+Vicente+Ordonez%2C+and+Dong+Yu%2E+2024b%2E+Parallel%2Dspec%3A+Parallel+drafter+for+efficient+speculative+decoding%2E+arXiv+preprint+arXiv%3A2410%2E05589%2E+%E2%80%94+%5BarXiv%3A2410)
192. Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou. 2024. Show-o: One single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528. — [arXiv:2408.12528](https://arxiv.org/abs/2408.12528) [find](https://scholar.google.com/scholar?q=Jinheng+Xie%2C+Weijia+Mao%2C+Zechen+Bai%2C+David+Junhao+Zhang%2C+Weihao+Wang%2C+Kevin+Qinghong+Lin%2C+Yuchao+Gu%2C+Zhijie+Chen%2C+Zhenheng+Yang%2C+and+Mike+Zheng+Shou%2E+2024%2E+Show%2Do%3A+One+single+transformer+to+unify+mult)
193. Roy Xie, David Qiu, Deepak Gopinath, Dong Lin, Yanchao Sun, Chong Wang, Saloni Potdar, and Bhuwan Dhingra. 2025. Interleaved reasoning for large language models via reinforcement learning. arXiv preprint arXiv:2505.19640. — [arXiv:2505.19640](https://arxiv.org/abs/2505.19640) [find](https://scholar.google.com/scholar?q=Roy+Xie%2C+David+Qiu%2C+Deepak+Gopinath%2C+Dong+Lin%2C+Yanchao+Sun%2C+Chong+Wang%2C+Saloni+Potdar%2C+and+Bhuwan+Dhingra%2E+2025%2E+Interleaved+reasoning+for+large+language+models+via+reinforcement+learning%2E+arXiv+prepr)
194. Zhifei Xie and Changqiao Wu. 2024. Mini-omni: Language models can hear, talk while thinking in streaming. arXiv preprint arXiv:2408.16725. [find](https://scholar.google.com/scholar?q=Zhifei+Xie+and+Changqiao+Wu%2E+2024%2E+Mini%2Domni%3A+Language+models+can+hear%2C+talk+while+thinking+in+streaming%2E+arXiv+preprint+arXiv%3A2408%2E16725%2E)
195. Yi Xin, Qi Qin, Siqi Luo, Kaiwen Zhu, Juncheng Yan, Yan Tai, Jiayi Lei, Yuewen Cao, Keqi Wang, Yibin Wang, et al. 2025. Lumina-dimoo: An omni diffusion large language model for multimodal generation and understanding. arXiv preprint arXiv:2510.06308. — [arXiv:2510.06308](https://arxiv.org/abs/2510.06308) [find](https://scholar.google.com/scholar?q=Yi+Xin%2C+Qi+Qin%2C+Siqi+Luo%2C+Kaiwen+Zhu%2C+Juncheng+Yan%2C+Yan+Tai%2C+Jiayi+Lei%2C+Yuewen+Cao%2C+Keqi+Wang%2C+Yibin+Wang%2C+et+al%2E+2025%2E+Lumina%2Ddimoo%3A+An+omni+diffusion+large+language+model+for+multimodal+generation+a)
196. Z Xin, Z Dong, L Shimin, Z Yaqian, and Q Xipeng. 2024. Speechtokenizer: Unified speech tokenizer for speech language models. In Proc. Int. Conf. Learn. Representations, pages 1–21. [find](https://scholar.google.com/scholar?q=Z+Xin%2C+Z+Dong%2C+L+Shimin%2C+Z+Yaqian%2C+and+Q+Xipeng%2E+2024%2E+Speechtokenizer%3A+Unified+speech+tokenizer+for+speech+language+models%2E+In+Proc%2E+Int%2E+Conf%2E+Learn%2E+Representations%2C+pages+1%E2%80%9321%2E)
197. Boxun Xu, Yu Wang, Zihu Wang, and Peng Li. 2025a. Ams-kv: Adaptive kv caching in multi-scale visual autoregressive transformers. arXiv preprint arXiv:2511.16047. — [arXiv:2511.16047](https://arxiv.org/abs/2511.16047) [find](https://scholar.google.com/scholar?q=Boxun+Xu%2C+Yu+Wang%2C+Zihu+Wang%2C+and+Peng+Li%2E+2025a%2E+Ams%2Dkv%3A+Adaptive+kv+caching+in+multi%2Dscale+visual+autoregressive+transformers%2E+arXiv+preprint+arXiv%3A2511%2E16047%2E+%E2%80%94+%5BarXiv%3A2511%2E16047%5D%28https%3A%2F%2Farxiv%2Eorg)
198. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, et al. 2025b. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215. — [Qwen2.5-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen2-5-omni-technical/)
199. Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu,… — [Qwen3-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen3-omni-technical-report/)
200. Songlin Yang, Bailin Wang, Yu Zhang, Yikang Shen, and Yoon Kim. 2024b. Parallelizing linear transformers with the delta rule over sequence length. Advances in neural information processing systems, 37:115491–115522. [find](https://scholar.google.com/scholar?q=Songlin+Yang%2C+Bailin+Wang%2C+Yu+Zhang%2C+Yikang+Shen%2C+and+Yoon+Kim%2E+2024b%2E+Parallelizing+linear+transformers+with+the+delta+rule+over+sequence+length%2E+Advances+in+neural+information+processing+systems%2C+37)
201. Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, and Song Han. 2025d. Stream-ingvlm: Real-time understanding for infinite video streams. arXiv preprint arXiv:2510.09608. [find](https://scholar.google.com/scholar?q=Ruyi+Xu%2C+Guangxuan+Xiao%2C+Yukang+Chen%2C+Liuning+He%2C+Kelly+Peng%2C+Yao+Lu%2C+and+Song+Han%2E+2025d%2E+Stream%2Dingvlm%3A+Real%2Dtime+understanding+for+infinite+video+streams%2E+arXiv+preprint+arXiv%3A2510%2E09608%2E)
202. Yifan Yang, Shujie Liu, Jinyu Li, Yuxuan Hu, Haibin Wu, Hui Wang, Jianwei Yu, Lingwei Meng, Haiyang Sun, Yanqing Liu, et al. 2025f. Pseudo-autoregressive neural codec language models for efficient zero-shot text-to-speech synthesis. In Proceedings of the 33rd ACM International Conference on Multimed… [find](https://scholar.google.com/scholar?q=Yifan+Yang%2C+Shujie+Liu%2C+Jinyu+Li%2C+Yuxuan+Hu%2C+Haibin+Wu%2C+Hui+Wang%2C+Jianwei+Yu%2C+Lingwei+Meng%2C+Haiyang+Sun%2C+Yanqing+Liu%2C+et+al%2E+2025f%2E+Pseudo%2Dautoregressive+neural+codec+language+models+for+efficient+zer)
203. Ting Xu, Zhichao Huang, Jiankai Sun, Shanbo Cheng, and Wai Lam. 2025e. Seqpo-simt: Sequential policy optimization for simultaneous machine translation. arXiv preprint arXiv:2505.20622. [find](https://scholar.google.com/scholar?q=Ting+Xu%2C+Zhichao+Huang%2C+Jiankai+Sun%2C+Shanbo+Cheng%2C+and+Wai+Lam%2E+2025e%2E+Seqpo%2Dsimt%3A+Sequential+policy+optimization+for+simultaneous+machine+translation%2E+arXiv+preprint+arXiv%3A2505%2E20622%2E)
204. Yechen Xu, Xinhao Kong, Tingjun Chen, and Danyang Zhuo. 2024. Conveyor: Efficient tool-aware llm serving with tool partial execution. arXiv preprint arXiv:2406.00059. — [arXiv:2406.00059](https://arxiv.org/abs/2406.00059) [find](https://scholar.google.com/scholar?q=Yechen+Xu%2C+Xinhao+Kong%2C+Tingjun+Chen%2C+and+Danyang+Zhuo%2E+2024%2E+Conveyor%3A+Efficient+tool%2Daware+llm+serving+with+tool+partial+execution%2E+arXiv+preprint+arXiv%3A2406%2E00059%2E+%E2%80%94+%5BarXiv%3A2406%2E00059%5D%28https%3A%2F%2Farxi)
205. George Yakushev, Nataliia Babina, Masoud Vahid Dast-gerdi, Vyacheslav Zhdanovskiy, Alina Shutova, and Denis Kuznedelev. 2025. Asynchronous reasoning: Training-free interactive thinking llms. arXiv preprint arXiv:2512.10931. [find](https://scholar.google.com/scholar?q=George+Yakushev%2C+Nataliia+Babina%2C+Masoud+Vahid+Dast%2Dgerdi%2C+Vyacheslav+Zhdanovskiy%2C+Alina+Shutova%2C+and+Denis+Kuznedelev%2E+2025%2E+Asynchronous+reasoning%3A+Training%2Dfree+interactive+thinking+llms%2E+arXiv+pre)
206. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
207. Dongjie Yang, XiaoDong Han, Yan Gao, Yao Hu, Shilin Zhang, and Hai Zhao. 2024a. [Pyramidinfer: Pyramid kv cache compression for high-throughput llm inference](https://md.research.elamur.ai/free/en/papers/yang-2024-pyramidinfer-pyramid-kv-cache-compression/). arXiv preprint arXiv:2405.12532.
208. Haolin Yang, Feilong Tang, Lingxiao Zhao, Xiang An, Ming Hu, Huifa Li, Xinlin Zhuang, Yifan Lu, Xiaofeng Zhang, Abdalla Swikir, et al. 2025b. Streamagent: Towards anticipatory agents for streaming video understanding. arXiv preprint arXiv:2508.01875. — [arXiv:2508.01875](https://arxiv.org/abs/2508.01875) [find](https://scholar.google.com/scholar?q=Haolin+Yang%2C+Feilong+Tang%2C+Lingxiao+Zhao%2C+Xiang+An%2C+Ming+Hu%2C+Huifa+Li%2C+Xinlin+Zhuang%2C+Yifan+Lu%2C+Xiaofeng+Zhang%2C+Abdalla+Swikir%2C+et+al%2E+2025b%2E+Streamagent%3A+Towards+anticipatory+agents+for+streaming+vid)
209. Ling Yang, Ye Tian, Bowen Li, Xinchen Zhang, Ke Shen, Yunhai Tong, and Mengdi Wang. 2025c. Mmada: Multimodal large diffusion language models. arXiv preprint arXiv:2505.15809. — [arXiv:2505.15809](https://arxiv.org/abs/2505.15809) [find](https://scholar.google.com/scholar?q=Ling+Yang%2C+Ye+Tian%2C+Bowen+Li%2C+Xinchen+Zhang%2C+Ke+Shen%2C+Yunhai+Tong%2C+and+Mengdi+Wang%2E+2025c%2E+Mmada%3A+Multimodal+large+diffusion+language+models%2E+arXiv+preprint+arXiv%3A2505%2E15809%2E+%E2%80%94+%5BarXiv%3A2505%2E15809%5D%28http)
210. Shang Yang, Junxian Guo, Haotian Tang, Qinghao Hu, Guangxuan Xiao, Jiaming Tang, Yujun Lin, Zhijian Liu, Yao Lu, and Song Han. 2025d. Lserve: Efficient long-sequence llm serving with unified sparse attention. arXiv preprint arXiv:2502.14866. — [arXiv:2502.14866](https://arxiv.org/abs/2502.14866) [find](https://scholar.google.com/scholar?q=Shang+Yang%2C+Junxian+Guo%2C+Haotian+Tang%2C+Qinghao+Hu%2C+Guangxuan+Xiao%2C+Jiaming+Tang%2C+Yujun+Lin%2C+Zhijian+Liu%2C+Yao+Lu%2C+and+Song+Han%2E+2025d%2E+Lserve%3A+Efficient+long%2Dsequence+llm+serving+with+unified+sparse+at)
211. Songlin Yang, Bailin Wang, Yikang Shen, Rameswar Panda, and Yoon Kim. 2023. Gated linear attention transformers with hardware-efficient training. arXiv preprint arXiv:2312.06635. [find](https://scholar.google.com/scholar?q=Songlin+Yang%2C+Bailin+Wang%2C+Yikang+Shen%2C+Rameswar+Panda%2C+and+Yoon+Kim%2E+2023%2E+Gated+linear+attention+transformers+with+hardware%2Defficient+training%2E+arXiv+preprint+arXiv%3A2312%2E06635%2E)
212. Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla, Aashu Singh, Shlok Kumar Mishra, Lizhu Zhang, and Mengye Ren. 2025e. Streammem: Query-agnostic kv cache memory for streaming video understanding. arXiv preprint arXiv:2508.15717. — [arXiv:2508.15717](https://arxiv.org/abs/2508.15717) [find](https://scholar.google.com/scholar?q=Yanlai+Yang%2C+Zhuokai+Zhao%2C+Satya+Narayan+Shukla%2C+Aashu+Singh%2C+Shlok+Kumar+Mishra%2C+Lizhu+Zhang%2C+and+Mengye+Ren%2E+2025e%2E+Streammem%3A+Query%2Dagnostic+kv+cache+memory+for+streaming+video+understanding%2E+arXiv)
213. Yifan Yang, Ziyang Ma, Shujie Liu, Jinyu Li, Hui Wang, Lingwei Meng, Haiyang Sun, Yuzhe Liang, Ruiyang Xu, Yuxuan Hu, et al. 2024c. Interleaved speech-text language models are simple streaming text to speech synthesizers. arXiv preprint arXiv:2412.16102. — [arXiv:2412.16102](https://arxiv.org/abs/2412.16102) [find](https://scholar.google.com/scholar?q=Yifan+Yang%2C+Ziyang+Ma%2C+Shujie+Liu%2C+Jinyu+Li%2C+Hui+Wang%2C+Lingwei+Meng%2C+Haiyang+Sun%2C+Yuzhe+Liang%2C+Ruiyang+Xu%2C+Yuxuan+Hu%2C+et+al%2E+2024c%2E+Interleaved+speech%2Dtext+language+models+are+simple+streaming+text+to)
214. Zeyu Yang, Lai Wei, Roman Koshkin, Xi Chen, and Satoshi Nakamura. 2025g. Sasst: Leveraging syntax-aware chunking and llms for simultaneous speech translation. arXiv preprint arXiv:2508.07781. [find](https://scholar.google.com/scholar?q=Zeyu+Yang%2C+Lai+Wei%2C+Roman+Koshkin%2C+Xi+Chen%2C+and+Satoshi+Nakamura%2E+2025g%2E+Sasst%3A+Leveraging+syntax%2Daware+chunking+and+llms+for+simultaneous+speech+translation%2E+arXiv+preprint+arXiv%3A2508%2E07781%2E)
215. Zhenyu Yang, Yuhang Hu, Zemin Du, Dizhan Xue, Shengsheng Qian, Jiahong Wu, Fan Yang, Weiming Dong, and Changsheng Xu. 2025h. Svbench: A benchmark with temporal multi-turn dialogues for streaming video understanding. arXiv preprint arXiv:2502.10810. — [arXiv:2502.10810](https://arxiv.org/abs/2502.10810) [find](https://scholar.google.com/scholar?q=Zhenyu+Yang%2C+Yuhang+Hu%2C+Zemin+Du%2C+Dizhan+Xue%2C+Shengsheng+Qian%2C+Jiahong+Wu%2C+Fan+Yang%2C+Weiming+Dong%2C+and+Changsheng+Xu%2E+2025h%2E+Svbench%3A+A+benchmark+with+temporal+multi%2Dturn+dialogues+for+streaming+video)
216. Zhenyu Yang, Kairui Zhang, Yuhang Hu, Bing Wang, Shengsheng Qian, Bin Wen, Fan Yang, Tingting Gao, Weiming Dong, and Changsheng Xu. 2025i. Livestar: Live streaming assistant for real-world online video understanding. arXiv preprint arXiv:2511.05299. — [arXiv:2511.05299](https://arxiv.org/abs/2511.05299) [find](https://scholar.google.com/scholar?q=Zhenyu+Yang%2C+Kairui+Zhang%2C+Yuhang+Hu%2C+Bing+Wang%2C+Shengsheng+Qian%2C+Bin+Wen%2C+Fan+Yang%2C+Tingting+Gao%2C+Weiming+Dong%2C+and+Changsheng+Xu%2E+2025i%2E+Livestar%3A+Live+streaming+assistant+for+real%2Dworld+online+vide)
217. Moran Yanuka, Paul Dixon, Eyal Finkelshtein, Daniel Rotman, and Raja Giryes. 2025. Principled coarse-grained acceptance for speculative decoding in speech. arXiv preprint arXiv:2511.13732. — [arXiv:2511.13732](https://arxiv.org/abs/2511.13732) [find](https://scholar.google.com/scholar?q=Moran+Yanuka%2C+Paul+Dixon%2C+Eyal+Finkelshtein%2C+Daniel+Rotman%2C+and+Raja+Giryes%2E+2025%2E+Principled+coarse%2Dgrained+acceptance+for+speculative+decoding+in+speech%2E+arXiv+preprint+arXiv%3A2511%2E13732%2E+%E2%80%94+%5BarXiv%3A25)
218. Linli Yao, Yicheng Li, Yuancheng Wei, Lei Li, Shuhuai Ren, Yuanxin Liu, Kun Ouyang, Lean Wang, Shicheng Li, Sida Li, et al. 2025. Timechat-online: 80% visual tokens are naturally redundant in streaming videos. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 10807– 10816. [find](https://scholar.google.com/scholar?q=Linli+Yao%2C+Yicheng+Li%2C+Yuancheng+Wei%2C+Lei+Li%2C+Shuhuai+Ren%2C+Yuanxin+Liu%2C+Kun+Ouyang%2C+Lean+Wang%2C+Shicheng+Li%2C+Sida+Li%2C+et+al%2E+2025%2E+Timechat%2Donline%3A+80%25+visual+tokens+are+naturally+redundant+in+streamin)
219. Yao Yao, Zuchao Li, and Hai Zhao. 2024. Sirllm: Streaming infinite retentive llm. arXiv preprint arXiv:2405.12528. [find](https://scholar.google.com/scholar?q=Yao+Yao%2C+Zuchao+Li%2C+and+Hai+Zhao%2E+2024%2E+Sirllm%3A+Streaming+infinite+retentive+llm%2E+arXiv+preprint+arXiv%3A2405%2E12528%2E)
220. Zhen Ye, Peiwen Sun, Jiahe Lei, Hongzhan Lin, Xu Tan, Zheqi Dai, Qiuqiang Kong, Jianyi Chen, Jiahao Pan, Qifeng Liu, et al. 2025. Codec does matter: Exploring the semantic shortcoming of codec for audio language model. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, page… [find](https://scholar.google.com/scholar?q=Zhen+Ye%2C+Peiwen+Sun%2C+Jiahe+Lei%2C+Hongzhan+Lin%2C+Xu+Tan%2C+Zheqi+Dai%2C+Qiuqiang+Kong%2C+Jianyi+Chen%2C+Jiahao+Pan%2C+Qifeng+Liu%2C+et+al%2E+2025%2E+Codec+does+matter%3A+Exploring+the+semantic+shortcoming+of+codec+for+aud)
221. Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8964– 8986. [find](https://scholar.google.com/scholar?q=Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pages+8964%E2%80%93+8986%2E)
222. Tianwei Yin, Qiang Zhang, Richard Zhang, William T Freeman, Fredo Durand, Eli Shechtman, and Xun Huang. 2025. From slow bidirectional to fast autoregressive video diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 22963–22974. [find](https://scholar.google.com/scholar?q=Tianwei+Yin%2C+Qiang+Zhang%2C+Richard+Zhang%2C+William+T+Freeman%2C+Fredo+Durand%2C+Eli+Shechtman%2C+and+Xun+Huang%2E+2025%2E+From+slow+bidirectional+to+fast+autoregressive+video+diffusion+models%2E+In+Proceedings+of+t)
223. Shaolei Zhang and Yang Feng. 2023. End-to-end simultaneous speech translation with differentiable segmentation. arXiv preprint arXiv:2305.16093. [find](https://scholar.google.com/scholar?q=Shaolei+Zhang+and+Yang+Feng%2E+2023%2E+End%2Dto%2Dend+simultaneous+speech+translation+with+differentiable+segmentation%2E+arXiv+preprint+arXiv%3A2305%2E16093%2E)
224. Wenyi Yu, Siyin Wang, Xiaoyu Yang, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Guangzhi Sun, Lu Lu, Yuxuan Wang, and Chao Zhang. 2024. Salmonn-omni: A codec-free LLM for full-duplex speech understanding and generation. arXiv preprint arXiv:2411.18138. — [arXiv:2411.18138](https://arxiv.org/abs/2411.18138) [find](https://scholar.google.com/scholar?q=Wenyi+Yu%2C+Siyin+Wang%2C+Xiaoyu+Yang%2C+Xianzhao+Chen%2C+Xiaohai+Tian%2C+Jun+Zhang%2C+Guangzhi+Sun%2C+Lu+Lu%2C+Yuxuan+Wang%2C+and+Chao+Zhang%2E+2024%2E+Salmonn%2Domni%3A+A+codec%2Dfree+LLM+for+full%2Dduplex+speech+understanding+a)
225. Neil Zeghidour, Eugene Kharitonov, Manu Orsini, Václav Volhejn, Gabriel de Marmiesse, Edouard Grave, Patrick Pérez, Laurent Mazaré, and Alexandre Défossez. 2025. Streaming sequence-to-sequence learning with delayed streams modeling. arXiv preprint arXiv:2509.08753. — [arXiv:2509.08753](https://arxiv.org/abs/2509.08753) [find](https://scholar.google.com/scholar?q=Neil+Zeghidour%2C+Eugene+Kharitonov%2C+Manu+Orsini%2C+V%C3%A1clav+Volhejn%2C+Gabriel+de+Marmiesse%2C+Edouard+Grave%2C+Patrick+P%C3%A9rez%2C+Laurent+Mazar%C3%A9%2C+and+Alexandre+D%C3%A9fossez%2E+2025%2E+Streaming+sequence%2Dto%2Dsequence+learnin)
226. Xiangyu Zeng, Kefan Qiu, Qingyu Zhang, Xinhao Li, Jing Wang, Jiaxin Li, Ziang Yan, Kun Tian, Meng Tian, Xinhai Zhao, et al. 2025. Streamforest: Efficient online video understanding with persistent event memory. arXiv preprint arXiv:2509.24871. — [arXiv:2509.24871](https://arxiv.org/abs/2509.24871) [find](https://scholar.google.com/scholar?q=Xiangyu+Zeng%2C+Kefan+Qiu%2C+Qingyu+Zhang%2C+Xinhao+Li%2C+Jing+Wang%2C+Jiaxin+Li%2C+Ziang+Yan%2C+Kun+Tian%2C+Meng+Tian%2C+Xinhai+Zhao%2C+et+al%2E+2025%2E+Streamforest%3A+Efficient+online+video+understanding+with+persistent+eve)
227. Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, and Xipeng Qiu. 2023a. [Speechgpt: Empowering large language models with intrinsic cross-modal conversational abilities](https://md.research.elamur.ai/free/en/papers/zhang-2023-speechgpt-empowering-large-language-models/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15757–15773.
228. Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024a. [Mm-llms: Recent advances in multimodal large language models](https://md.research.elamur.ai/free/en/papers/zhang-2024-mm-llms-recent-advances-multimodal/). arXiv preprint arXiv:2401.13601.
229. Gengyuan Zhang, Tanveer Hannan, Hermine Kleiner, Beste Aydemir, Xinyu Xie, Jian Lan, Thomas Seidl, Volker Tresp, and Jindong Gu. 2025a. Avila: Asynchronous vision-language agent for streaming multimodal data interaction. arXiv preprint arXiv:2506.18472. — [arXiv:2506.18472](https://arxiv.org/abs/2506.18472) [find](https://scholar.google.com/scholar?q=Gengyuan+Zhang%2C+Tanveer+Hannan%2C+Hermine+Kleiner%2C+Beste+Aydemir%2C+Xinyu+Xie%2C+Jian+Lan%2C+Thomas+Seidl%2C+Volker+Tresp%2C+and+Jindong+Gu%2E+2025a%2E+Avila%3A+Asynchronous+vision%2Dlanguage+agent+for+streaming+multimod)
230. Haoji Zhang, Yiqin Wang, Yansong Tang, Yong Liu, Jiashi Feng, Jifeng Dai, and Xiaojie Jin. 2024b. Flash-vstream: Memory-based real-time understanding for long video streams. arXiv preprint arXiv:2406.08085. — [arXiv:2406.08085](https://arxiv.org/abs/2406.08085) [find](https://scholar.google.com/scholar?q=Haoji+Zhang%2C+Yiqin+Wang%2C+Yansong+Tang%2C+Yong+Liu%2C+Jiashi+Feng%2C+Jifeng+Dai%2C+and+Xiaojie+Jin%2E+2024b%2E+Flash%2Dvstream%3A+Memory%2Dbased+real%2Dtime+understanding+for+long+video+streams%2E+arXiv+preprint+arXiv%3A2406%2E)
231. Jialiang Zhang, Junlong Tong, Junyan Lin, Hao Wu, , Yirong Sun, Yunpu Ma, and Xiaoyu Shen. 2026. Think-as-you-see: Streaming chain-of-thought reasoning for large vision-language models. arXiv preprint arXiv:2603.02872. — [arXiv:2603.02872](https://arxiv.org/abs/2603.02872) [find](https://scholar.google.com/scholar?q=Jialiang+Zhang%2C+Junlong+Tong%2C+Junyan+Lin%2C+Hao+Wu%2C+%2C+Yirong+Sun%2C+Yunpu+Ma%2C+and+Xiaoyu+Shen%2E+2026%2E+Think%2Das%2Dyou%2Dsee%3A+Streaming+chain%2Dof%2Dthought+reasoning+for+large+vision%2Dlanguage+models%2E+arXiv+preprint)
232. Shaolei Zhang, Qingkai Fang, Shoutao Guo, Zhengrui Ma, Min Zhang, and Yang Feng. 2024c. Streamspeech: Simultaneous speech-to-speech translation with multi-task learning. In Proceedings of the 62nd Shaolei Zhang, Shoutao Guo, Qingkai Fang, Yan Zhou, and Yang Feng. 2025b. Stream-omni: Simultaneous mul… [find](https://scholar.google.com/scholar?q=Shaolei+Zhang%2C+Qingkai+Fang%2C+Shoutao+Guo%2C+Zhengrui+Ma%2C+Min+Zhang%2C+and+Yang+Feng%2E+2024c%2E+Streamspeech%3A+Simultaneous+speech%2Dto%2Dspeech+translation+with+multi%2Dtask+learning%2E+In+Proceedings+of+the+62nd+Sha)
233. Xuan Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, and Min Lin. 2024d. Simlayerkv: A simple framework for layer-level kv cache reduction. [find](https://scholar.google.com/scholar?q=Xuan+Zhang%2C+Cunxiao+Du%2C+Chao+Du%2C+Tianyu+Pang%2C+Wei+Gao%2C+and+Min+Lin%2E+2024d%2E+Simlayerkv%3A+A+simple+framework+for+layer%2Dlevel+kv+cache+reduction%2E)
234. Yanqi Zhang, Yuwei Hu, Runyuan Zhao, John Lui, and Haibo Chen. 2024e. Unifying kv cache compression for large language models with leankv. arXiv preprint arXiv:2412.03131. [find](https://scholar.google.com/scholar?q=Yanqi+Zhang%2C+Yuwei+Hu%2C+Runyuan+Zhao%2C+John+Lui%2C+and+Haibo+Chen%2E+2024e%2E+Unifying+kv+cache+compression+for+large+language+models+with+leankv%2E+arXiv+preprint+arXiv%3A2412%2E03131%2E)
235. Yichi Zhang, Xin Luna Dong, Zhaojiang Lin, Andrea Madotto, Anuj Kumar, Babak Damavandi, Joyce Chai, and Seungwhan Moon. 2025c. Proactive assistant dialogue generation from streaming egocentric videos. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 12… [find](https://scholar.google.com/scholar?q=Yichi+Zhang%2C+Xin+Luna+Dong%2C+Zhaojiang+Lin%2C+Andrea+Madotto%2C+Anuj+Kumar%2C+Babak+Damavandi%2C+Joyce+Chai%2C+and+Seungwhan+Moon%2E+2025c%2E+Proactive+assistant+dialogue+generation+from+streaming+egocentric+videos%2E)
236. Yulin Zhang, Cheng Shi, Yang Wang, and Sibei Yang. 2025d. Eyes wide open: Ego proactive video-llm for streaming video. arXiv preprint arXiv:2510.14560. — [arXiv:2510.14560](https://arxiv.org/abs/2510.14560) [find](https://scholar.google.com/scholar?q=Yulin+Zhang%2C+Cheng+Shi%2C+Yang+Wang%2C+and+Sibei+Yang%2E+2025d%2E+Eyes+wide+open%3A+Ego+proactive+video%2Dllm+for+streaming+video%2E+arXiv+preprint+arXiv%3A2510%2E14560%2E+%E2%80%94+%5BarXiv%3A2510%2E14560%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2510%2E)
237. Zekai Zhang, Weiye Zhu, Hewei Pan, Xiangchen Wang, Rongtao Xu, Xing Sun, and Feng Zheng. 2025e. Activevln: Towards active exploration via multi-turn rl in vision-and-language navigation. arXiv preprint arXiv:2509.12618. — [arXiv:2509.12618](https://arxiv.org/abs/2509.12618) [find](https://scholar.google.com/scholar?q=Zekai+Zhang%2C+Weiye+Zhu%2C+Hewei+Pan%2C+Xiangchen+Wang%2C+Rongtao+Xu%2C+Xing+Sun%2C+and+Feng+Zheng%2E+2025e%2E+Activevln%3A+Towards+active+exploration+via+multi%2Dturn+rl+in+vision%2Dand%2Dlanguage+navigation%2E+arXiv+preprin)
238. Zeyu Zhang, Shuning Chang, Yuanyu He, Yizeng Han, Jiasheng Tang, Fan Wang, and Bohan Zhuang. 2025f. Blockvid: Block diffusion for high-quality and consistent minute-long video generation. arXiv preprint arXiv:2511.22973. — [arXiv:2511.22973](https://arxiv.org/abs/2511.22973) [find](https://scholar.google.com/scholar?q=Zeyu+Zhang%2C+Shuning+Chang%2C+Yuanyu+He%2C+Yizeng+Han%2C+Jiasheng+Tang%2C+Fan+Wang%2C+and+Bohan+Zhuang%2E+2025f%2E+Blockvid%3A+Block+diffusion+for+high%2Dquality+and+consistent+minute%2Dlong+video+generation%2E+arXiv+prepri)
239. Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, et al. 2023b. H2o: Heavy-hitter oracle for efficient generative inference of large language models. Advances in Neural Information Processing Systems, 36:34661– 34… [find](https://scholar.google.com/scholar?q=Zhenyu+Zhang%2C+Ying+Sheng%2C+Tianyi+Zhou%2C+Tianlong+Chen%2C+Lianmin+Zheng%2C+Ruisi+Cai%2C+Zhao+Song%2C+Yuandong+Tian%2C+Christopher+R%C3%A9%2C+Clark+Barrett%2C+et+al%2E+2023b%2E+H2o%3A+Heavy%2Dhitter+oracle+for+efficient+generative)
240. Anhao Zhao, Fanghua Ye, Yingqi Fan, Junlong Tong, Zhiwei Fei, Hui Su, and Xiaoyu Shen. 2025a. Skipgpt: Dynamic layer pruning reinvented with token awareness and module decoupling. arXiv preprint arXiv:2506.04179. — [arXiv:2506.04179](https://arxiv.org/abs/2506.04179) [find](https://scholar.google.com/scholar?q=Anhao+Zhao%2C+Fanghua+Ye%2C+Yingqi+Fan%2C+Junlong+Tong%2C+Zhiwei+Fei%2C+Hui+Su%2C+and+Xiaoyu+Shen%2E+2025a%2E+Skipgpt%3A+Dynamic+layer+pruning+reinvented+with+token+awareness+and+module+decoupling%2E+arXiv+preprint+arXiv)
241. Libo Zhao, Jing Li, and Ziqian Zeng. 2024. Psfuture: A pseudo-future-based zero-shot adaptive policy for simultaneous machine translation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1869–1881. [find](https://scholar.google.com/scholar?q=Libo+Zhao%2C+Jing+Li%2C+and+Ziqian+Zeng%2E+2024%2E+Psfuture%3A+A+pseudo%2Dfuture%2Dbased+zero%2Dshot+adaptive+policy+for+simultaneous+machine+translation%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in)
242. Libo Zhao, Jing Li, and Ziqian Zeng. 2025b. Drfrattn: Directly learn adaptive policy from attention for simultaneous machine translation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 34881–34894. [find](https://scholar.google.com/scholar?q=Libo+Zhao%2C+Jing+Li%2C+and+Ziqian+Zeng%2E+2025b%2E+Drfrattn%3A+Directly+learn+adaptive+policy+from+attention+for+simultaneous+machine+translation%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Methods+in+)
243. Yucheng Zhao, Chong Luo, Chuanxin Tang, Dongdong Chen, Noel Codella, and Zheng-Jun Zha. 2023. Streaming video model. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14602–14612. [find](https://scholar.google.com/scholar?q=Yucheng+Zhao%2C+Chong+Luo%2C+Chuanxin+Tang%2C+Dongdong+Chen%2C+Noel+Codella%2C+and+Zheng%2DJun+Zha%2E+2023%2E+Streaming+video+model%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+recognitio)
244. W Zhong et al. 2024. Enhancing large language models with long-term memory. AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=W+Zhong+et+al%2E+2024%2E+Enhancing+large+language+models+with+long%2Dterm+memory%2E+AAAI+Conference+on+Artificial+Intelligence%2E)
245. Xiabin Zhou, Wenbin Wang, Minyan Zeng, Jiaxian Guo, Xuebo Liu, Li Shen, Min Zhang, and Liang Ding. 2024. Dynamickv: Task-aware adaptive kv cache compression for long context llms. arXiv preprint arXiv:2412.14838. [find](https://scholar.google.com/scholar?q=Xiabin+Zhou%2C+Wenbin+Wang%2C+Minyan+Zeng%2C+Jiaxian+Guo%2C+Xuebo+Liu%2C+Li+Shen%2C+Min+Zhang%2C+and+Liang+Ding%2E+2024%2E+Dynamickv%3A+Task%2Daware+adaptive+kv+cache+compression+for+long+context+llms%2E+arXiv+preprint+arXiv)
246. Qianchao Zhu, Jiangfei Duan, Chang Chen, Siran Liu, Xiuhong Li, Guanyu Feng, Xin Lv, Xiao Chuanfu, Dahua Lin, and Chao Yang. 2025. Sampleattention: Near-lossless acceleration of long context llm inference with adaptive structured sparse attention. Proceedings of Machine Learning and Systems, 7. [find](https://scholar.google.com/scholar?q=Qianchao+Zhu%2C+Jiangfei+Duan%2C+Chang+Chen%2C+Siran+Liu%2C+Xiuhong+Li%2C+Guanyu+Feng%2C+Xin+Lv%2C+Xiao+Chuanfu%2C+Dahua+Lin%2C+and+Chao+Yang%2E+2025%2E+Sampleattention%3A+Near%2Dlossless+acceleration+of+long+context+llm+infer)
247. Xianwei Zhuang, Yuxin Xie, Yufan Deng, Liming Liang, Jinghan Ru, Yuguo Yin, and Yuexian Zou. 2025. Vargpt: Unified understanding and generation in a visual autoregressive multimodal large language model. arXiv preprint arXiv:2501.12327. — [arXiv:2501.12327](https://arxiv.org/abs/2501.12327) [find](https://scholar.google.com/scholar?q=Xianwei+Zhuang%2C+Yuxin+Xie%2C+Yufan+Deng%2C+Liming+Liang%2C+Jinghan+Ru%2C+Yuguo+Yin%2C+and+Yuexian+Zou%2E+2025%2E+Vargpt%3A+Unified+understanding+and+generation+in+a+visual+autoregressive+multimodal+large+language+mod)

*Updated 31 October 2026*