---
title: "AutoSOTA — paper by Li et al. (2026) — summary and ideas"
description: "Pushing a published AI method beyond its reported results usually takes months of manual work. 129 references, cited by 5 papers here."
authors: ["Yu Li", "Chenyang Shao", "Xinyang Liu", "Ruotong Zhao", "Peijie Liu", "Hongyuan Su", "Zhibin Chen", "Qinglong Yang", "Anjie Xu", "Yi Fang", "Qingbin Zeng", "Tianxing Li", "Jingbo Xu", "Fengli Xu", "Yong Li", "Tie-Yan Liu"]
year: 2026
venue: "arXiv:2604.05550"
source: "https://arxiv.org/abs/2604.05550"
doi: "10.48550/arxiv.2604.05550"
arxiv: "2604.05550"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/li-2026-autosota-end-end-automated-research/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/li-2026-autosota-end-end-automated-research/)

[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/3/) / AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

# AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

**Authors:** [Yu Li](https://md.research.elamur.ai/free/en/authors/yu-li/), [Chenyang Shao](https://md.research.elamur.ai/free/en/authors/chenyang-shao/), Xinyang Liu, Ruotong Zhao, Peijie Liu, Hongyuan Su, [Zhibin Chen](https://md.research.elamur.ai/free/en/authors/zhibin-chen/), Qinglong Yang, Anjie Xu, [Yi Fang](https://md.research.elamur.ai/free/en/authors/yi-fang/), Qingbin Zeng, Tianxing Li, Jingbo Xu, [Fengli Xu](https://md.research.elamur.ai/free/en/authors/fengli-xu/), [Yong Li](https://md.research.elamur.ai/free/en/authors/yong-li/) and [Tie-Yan Liu](https://md.research.elamur.ai/free/en/authors/tie-yan-liu/) · **Year:** 2026 · **Venue:** arXiv:2604.05550 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2604.05550) · [PDF](https://arxiv.org/pdf/2604.05550) · [DOI 10.48550/arxiv.2604.05550](https://doi.org/10.48550/arxiv.2604.05550) · [arXiv 2604.05550](https://arxiv.org/abs/2604.05550) · [OpenAlex](https://openalex.org/W7151749990)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 5 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Pushing a published AI method beyond its reported results usually takes months of manual work. Researchers must find the code and data, get the repository running, reproduce the baseline, and only then try improvements. AutoSOTA automates this entire chain, starting from a paper and ending with an improved, runnable repository. The authors split the task into three linked phases. The first gathers resources and fixes the target metric. The second makes experiments run and evaluates them. The third reflects on results and proposes changes. The work is divided among eight cooperating LLM agents. Earlier tools such as AutoResearch only edit one module inside a clean sandbox. AutoSOTA instead handles environment setup, dependency repair and long experiments itself, while a supervising agent blocks illegitimate gains such as evaluation leakage. The system was tested on filtered papers from eight top AI conferences. It produced new SOTA results for 105 papers, improving on the originals by about 10% on average in roughly five hours per paper. This suggests agents can take over routine reproduction and tuning, giving human researchers more time for conceptual work.

## Key points
- **Agents:** the eight roles are AgentResource (links paper to repo and dependencies), AgentObjective (builds a tree-structured evaluation rubric), AgentInit, AgentMonitor (tracks runs and detects deadlocks), AgentFix, AgentIdeator, AgentScheduler and AgentSupervisor.
- **Paper selection:** papers from eight top-tier AI conferences were filtered by methodological relevance, public code, repository readiness and execution cost.
- **Results:** AutoSOTA found 105 new SOTA models, with an average gain of about 10% over the original main methods and about 5 hours of execution per paper.
- **Case studies:** these cover LLM, NLP, computer vision, time series, optimization and biology research. They show changes at the architectural, algorithmic and workflow level, not just hyperparameter tuning.
- **Lineage and next steps:** AgentSupervisor enforces a "red-line" rule set against protocol violations and shortcuts. The system builds on the authors' earlier OmniScientist agent, and its project page is tsinghua-fib-lab.github.io/AutoSOTA.

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

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 249 works · [🎯 Information Systems and Management](https://md.research.elamur.ai/free/en/shelves/decision-sciences/information-systems-and-management/) · 52 works

## Cite

Cite as: Yu Li, Chenyang Shao, Xinyang Liu, Ruotong Zhao, Peijie Liu, Hongyuan Su, Zhibin Chen, Qinglong Yang, Anjie Xu, Yi Fang, Qingbin Zeng, Tianxing Li, Jingbo Xu, Fengli Xu, Yong Li and Tie-Yan Liu. 2026. AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery. arXiv:2604.05550.

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

```bibtex
@misc{li2026autosota,
  title = {{AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery}},
  author = {Yu Li, Chenyang Shao, Xinyang Liu, Ruotong Zhao, Peijie Liu, Hongyuan Su, Zhibin Chen, Qinglong Yang, Anjie Xu, Yi Fang, Qingbin Zeng, Tianxing Li, Jingbo Xu, Fengli Xu, Yong Li and Tie-Yan Liu},
  year = {2026},
  doi = {10.48550/arxiv.2604.05550},
  eprint = {2604.05550},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2604.05550}
}
```

- [← previous Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework](https://md.research.elamur.ai/free/en/papers/dycke-2026-automatic-reviewers-fail-detect-faulty/)
- [next → Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation](https://md.research.elamur.ai/free/en/papers/tian-2026-beyond-literal-mapping-benchmarking-improving/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/)

## References

129 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Chenyang Shao, Dehao Huang, Yu Li, Keyu Zhao, Weiquan Lin, Yining Zhang, Qingbin Zeng, Zhiyu Chen, Tianxing Li, Yifei Huang, et al. Omniscientist: Toward a co-evolving ecosystem of human and ai scientists. arXiv preprint arXiv:2511.16931, 2025. — [arXiv:2511.16931](https://arxiv.org/abs/2511.16931) [find](https://scholar.google.com/scholar?q=Chenyang+Shao%2C+Dehao+Huang%2C+Yu+Li%2C+Keyu+Zhao%2C+Weiquan+Lin%2C+Yining+Zhang%2C+Qingbin+Zeng%2C+Zhiyu+Chen%2C+Tianxing+Li%2C+Yifei+Huang%2C+et+al%2E+Omniscientist%3A+Toward+a+co%2Devolving+ecosystem+of+human+and+ai+scient)
2. Rafael Barbudo, Sebastián Ventura, and José Raúl Romero. Eight years of automl: categorisation, review and trends. Knowledge and Information Systems, 65(12):5097–5149, 2023. [find](https://scholar.google.com/scholar?q=Rafael+Barbudo%2C+Sebasti%C3%A1n+Ventura%2C+and+Jos%C3%A9+Ra%C3%BAl+Romero%2E+Eight+years+of+automl%3A+categorisation%2C+review+and+trends%2E+Knowledge+and+Information+Systems%2C+65%2812%29%3A5097%E2%80%935149%2C+2023%2E)
3. Xin He, Kaiyong Zhao, and Xiaowen Chu. Automl: A survey of the state-of-the-art. Knowledge-based systems, 212:106622, 2021. [find](https://scholar.google.com/scholar?q=Xin+He%2C+Kaiyong+Zhao%2C+and+Xiaowen+Chu%2E+Automl%3A+A+survey+of+the+state%2Dof%2Dthe%2Dart%2E+Knowledge%2Dbased+systems%2C+212%3A106622%2C+2021%2E)
4. Shubhra Kanti Karmaker, Md Mahadi Hassan, Micah J Smith, Lei Xu, Chengxiang Zhai, and Kalyan Veeramachaneni. Automl to date and beyond: Challenges and opportunities. Acm computing surveys (csur), 54(8):1–36, 2021. [find](https://scholar.google.com/scholar?q=Shubhra+Kanti+Karmaker%2C+Md+Mahadi+Hassan%2C+Micah+J+Smith%2C+Lei+Xu%2C+Chengxiang+Zhai%2C+and+Kalyan+Veeramachaneni%2E+Automl+to+date+and+beyond%3A+Challenges+and+opportunities%2E+Acm+computing+surveys+%28csur%29%2C+54%288)
5. Yu Li, Lehui Li, Qingmin Liao, Fengli Xu, and Yong Li. Agentexpt: Automating ai experiment design with llm-based resource retrieval agent. arXiv preprint arXiv:2511.04921, 2025. — [arXiv:2511.04921](https://arxiv.org/abs/2511.04921) [find](https://scholar.google.com/scholar?q=Yu+Li%2C+Lehui+Li%2C+Qingmin+Liao%2C+Fengli+Xu%2C+and+Yong+Li%2E+Agentexpt%3A+Automating+ai+experiment+design+with+llm%2Dbased+resource+retrieval+agent%2E+arXiv+preprint+arXiv%3A2511%2E04921%2C+2025%2E+%E2%80%94+%5BarXiv%3A2511%2E04921%5D%28h)
6. Andrej Karpathy. Autoresearch. [https://github.com/karpathy/autoresearch](https://github.com/karpathy/autoresearch), 2026. GitHub repository. [↗](https://github.com/karpathy/autoresearch)
7. Alexander Novikov, Ngân Vũ, Marvin Eisenberger, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, Sergey Shirobokov, Borislav Kozlovskii, Francisco JR Ruiz, Abbas Mehrabian, et al. [Alphaevolve: A coding agent for scientific and algorithmic discovery](https://md.research.elamur.ai/free/en/papers/novikov-2025-alphaevolve-coding-agent-scientific-algorithmic/). arXiv preprint arXiv:2506.13131, 2025.
8. Giulio Starace, Oliver Jaffe, Dane Sherburn, James Aung, Jun Shern Chan, Leon Maksin, Rachel Dias, Evan Mays, Benjamin Kinsella, Wyatt Thompson, et al. Paperbench: Evaluating ai’s ability to replicate ai research. arXiv preprint arXiv:2504.[01848, 2025](https://md.research.elamur.ai/free/en/papers/starace-2025-paperbench-evaluating-ai-s/).
9. Yanzheng Xiang, Hanqi Yan, Shuyin Ouyang, Lin Gui, and Yulan He. Scireplicate-bench: Benchmarking llms in agent-driven algorithmic reproduction from research papers. arXiv preprint arXiv:2504.00255, 2025. [find](https://scholar.google.com/scholar?q=Yanzheng+Xiang%2C+Hanqi+Yan%2C+Shuyin+Ouyang%2C+Lin+Gui%2C+and+Yulan+He%2E+Scireplicate%2Dbench%3A+Benchmarking+llms+in+agent%2Ddriven+algorithmic+reproduction+from+research+papers%2E+arXiv+preprint+arXiv%3A2504%2E00255%2C+2)
10. Shuo Yan, Ruochen Li, Ziming Luo, Zimu Wang, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, and Xinya Du. LMR-BENCH: Evaluating LLM agent’s ability on reproducing language modeling research. In Christos Christodoulopo… [find](https://scholar.google.com/scholar?q=Shuo+Yan%2C+Ruochen+Li%2C+Ziming+Luo%2C+Zimu+Wang%2C+Daoyang+Li%2C+Liqiang+Jing%2C+Kaiyu+He%2C+Peilin+Wu%2C+Juntong+Ni%2C+George+Michalopoulos%2C+Yue+Zhang%2C+Ziyang+Zhang%2C+Mian+Zhang%2C+Zhiyu+Chen%2C+and+Xinya+Du%2E+LMR%2DBENCH%3A+)
11. Mingfei Chen, Zijun Cui, Xiulong Liu, Jinlin Xiang, Yang Zheng, Jingyuan Li, and Eli Shlizerman. Savvy: Spatial awareness via audio-visual llms through seeing and hearing. Advances in Neural Information Processing Systems, 38:118999–119038, 2026. [find](https://scholar.google.com/scholar?q=Mingfei+Chen%2C+Zijun+Cui%2C+Xiulong+Liu%2C+Jinlin+Xiang%2C+Yang+Zheng%2C+Jingyuan+Li%2C+and+Eli+Shlizerman%2E+Savvy%3A+Spatial+awareness+via+audio%2Dvisual+llms+through+seeing+and+hearing%2E+Advances+in+Neural+Informati)
12. Panagiotis D Grontas, Antonio Terpin, Efe C Balta, Raffaello D’Andrea, and John Lygeros. Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers. arXiv preprint arXiv:2508.10480, 2025. [find](https://scholar.google.com/scholar?q=Panagiotis+D+Grontas%2C+Antonio+Terpin%2C+Efe+C+Balta%2C+Raffaello+D%E2%80%99Andrea%2C+and+John+Lygeros%2E+Pinet%3A+Optimizing+hard%2Dconstrained+neural+networks+with+orthogonal+projection+layers%2E+arXiv+preprint+arXiv%3A2508)
13. Bryon Tjanaka, Henry Chen, Matthew C Fontaine, and Stefanos Nikolaidis. Discount model search for quality diversity optimization in high-dimensional measure spaces. arXiv preprint arXiv:2601.01082, 2026. — [arXiv:2601.01082](https://arxiv.org/abs/2601.01082) [find](https://scholar.google.com/scholar?q=Bryon+Tjanaka%2C+Henry+Chen%2C+Matthew+C+Fontaine%2C+and+Stefanos+Nikolaidis%2E+Discount+model+search+for+quality+diversity+optimization+in+high%2Ddimensional+measure+spaces%2E+arXiv+preprint+arXiv%3A2601%2E01082%2C+20)
14. Guoqi Yu, Juncheng Wang, Chen Yang, Jing Qin, Angelica I Aviles-Rivero, and Shujun Wang. Decentralized attention fails centralized signals: Rethinking transformers for medical time series. arXiv preprint arXiv:2602.18473, 2026. — [arXiv:2602.18473](https://arxiv.org/abs/2602.18473) [find](https://scholar.google.com/scholar?q=Guoqi+Yu%2C+Juncheng+Wang%2C+Chen+Yang%2C+Jing+Qin%2C+Angelica+I+Aviles%2DRivero%2C+and+Shujun+Wang%2E+Decentralized+attention+fails+centralized+signals%3A+Rethinking+transformers+for+medical+time+series%2E+arXiv+prepr)
15. Usha Bhalla, Alex Oesterling, Claudio Mayrink Verdun, Himabindu Lakkaraju, and Flavio P Calmon. Temporal sparse autoencoders: Leveraging the sequential nature of language for interpretability. arXiv preprint arXiv:2511.05541, 2025. — [arXiv:2511.05541](https://arxiv.org/abs/2511.05541) [find](https://scholar.google.com/scholar?q=Usha+Bhalla%2C+Alex+Oesterling%2C+Claudio+Mayrink+Verdun%2C+Himabindu+Lakkaraju%2C+and+Flavio+P+Calmon%2E+Temporal+sparse+autoencoders%3A+Leveraging+the+sequential+nature+of+language+for+interpretability%2E+arXiv+p)
16. Yuezhou Ma, Haixu Wu, Hang Zhou, Huikun Weng, Jianmin Wang, and Mingsheng Long. Physense: Sensor placement optimization for accurate physics sensing. Advances in Neural Information Processing Systems, 38:35697–35725, 2026. [find](https://scholar.google.com/scholar?q=Yuezhou+Ma%2C+Haixu+Wu%2C+Hang+Zhou%2C+Huikun+Weng%2C+Jianmin+Wang%2C+and+Mingsheng+Long%2E+Physense%3A+Sensor+placement+optimization+for+accurate+physics+sensing%2E+Advances+in+Neural+Information+Processing+Systems%2C)
17. Shijie Zhao, Xuanyu Zhang, Weiqi Li, Junlin Li, Li Zhang, Tianfan Xue, and Jian Zhang. Reasoning as representation: Rethinking visual reinforcement learning in image quality assessment. arXiv preprint arXiv:2510.11369, 2025. — [arXiv:2510.11369](https://arxiv.org/abs/2510.11369) [find](https://scholar.google.com/scholar?q=Shijie+Zhao%2C+Xuanyu+Zhang%2C+Weiqi+Li%2C+Junlin+Li%2C+Li+Zhang%2C+Tianfan+Xue%2C+and+Jian+Zhang%2E+Reasoning+as+representation%3A+Rethinking+visual+reinforcement+learning+in+image+quality+assessment%2E+arXiv+preprint)
18. Zhengyang Geng, Mingyang Deng, Xingjian Bai, Zico Kolter, and Kaiming He. Mean flows for one-step generative modeling. Advances in Neural Information Processing Systems, 38:75460–75482, 2026. [find](https://scholar.google.com/scholar?q=Zhengyang+Geng%2C+Mingyang+Deng%2C+Xingjian+Bai%2C+Zico+Kolter%2C+and+Kaiming+He%2E+Mean+flows+for+one%2Dstep+generative+modeling%2E+Advances+in+Neural+Information+Processing+Systems%2C+38%3A75460%E2%80%9375482%2C+2026%2E)
19. Josh Givens, Song Liu, and Henry Reeve. Score matching with missing data. In International Conference on Machine Learning, pages 19523–19561. PMLR, 2025. [find](https://scholar.google.com/scholar?q=Josh+Givens%2C+Song+Liu%2C+and+Henry+Reeve%2E+Score+matching+with+missing+data%2E+In+International+Conference+on+Machine+Learning%2C+pages+19523%E2%80%9319561%2E+PMLR%2C+2025%2E)
20. Angéline Pouget, Mohammad Yaghini, Stephan Rabanser, and Nicolas Papernot. Suitability filter: A statistical framework for classifier evaluation in real-world deployment settings. In International Conference on Machine Learning, pages 49603–49627. PMLR, 2025. [find](https://scholar.google.com/scholar?q=Ang%C3%A9line+Pouget%2C+Mohammad+Yaghini%2C+Stephan+Rabanser%2C+and+Nicolas+Papernot%2E+Suitability+filter%3A+A+statistical+framework+for+classifier+evaluation+in+real%2Dworld+deployment+settings%2E+In+International+Con)
21. Zhiyuan Yan, Jiangming Wang, Peng Jin, Ke-Yue Zhang, Chengchun Liu, Shen Chen, Taiping Yao, Shouhong Ding, Baoyuan Wu, and Li Yuan. Orthogonal subspace decomposition for generalizable ai-generated image detection. In International Conference on Machine Learning, pages 70268–70288. PMLR, 2025. [find](https://scholar.google.com/scholar?q=Zhiyuan+Yan%2C+Jiangming+Wang%2C+Peng+Jin%2C+Ke%2DYue+Zhang%2C+Chengchun+Liu%2C+Shen+Chen%2C+Taiping+Yao%2C+Shouhong+Ding%2C+Baoyuan+Wu%2C+and+Li+Yuan%2E+Orthogonal+subspace+decomposition+for+generalizable+ai%2Dgenerated+ima)
22. Mengzhao Chen, Wenqi Shao, Peng Xu, Jiahao Wang, Peng Gao, Kaipeng Zhang, and Ping Luo. [Efficientqat: Efficient quantization-aware training for large language models](https://md.research.elamur.ai/free/en/papers/chen-2025-efficientqat-efficient-quantization-aware-training/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10081–10100…
23. Honghua Dong, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J Maddison, and Xujie Si. Appl: A prompt programming language for harmonious integration of programs and large language model prompts. In Proceedings of the 63rd Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Honghua+Dong%2C+Qidong+Su%2C+Yubo+Gao%2C+Zhaoyu+Li%2C+Yangjun+Ruan%2C+Gennady+Pekhimenko%2C+Chris+J+Maddison%2C+and+Xujie+Si%2E+Appl%3A+A+prompt+programming+language+for+harmonious+integration+of+programs+and+large+lan)
24. Hao Li, Xiaogeng Liu, Ning Zhang, and Chaowei Xiao. [Piguard: Prompt injection guardrail via mitigating overdefense for free](https://md.research.elamur.ai/free/en/papers/li-2025-piguard-prompt-injection-guardrail-mitigating/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 30420–30437, 2025.
25. Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, et al. [Fr-spec: Accelerating large-vocabulary language models via frequency-ranked speculative sampling](https://md.research.elamur.ai/free/en/papers/zhao-2025-fr-spec-accelerating-large-vocabulary/). In Proceedings of the 63rd Annual Meeting of the Association for Computational…
26. Qizhi Pei, Lijun Wu, Zhuoshi Pan, Yu Li, Honglin Lin, Chenlin Ming, Xin Gao, Conghui He, and Rui Yan. [Mathfusion: Enhancing mathematical problem-solving of llm through instruction fusion](https://md.research.elamur.ai/free/en/papers/pei-2025-mathfusion-enhancing-mathematical-problem-solving/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper…
27. Shuguo Hu, Jun Hu, and Huaiwen Zhang. Synergizing llms with global label propagation for multimodal fake news detection. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1426–1440, 2025. [find](https://scholar.google.com/scholar?q=Shuguo+Hu%2C+Jun+Hu%2C+and+Huaiwen+Zhang%2E+Synergizing+llms+with+global+label+propagation+for+multimodal+fake+news+detection%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+)
28. Bohan Zhang, Xiaokang Zhang, Jing Zhang, Jifan Yu, Sijia Luo, and Jie Tang. Cot-based synthesizer: Enhancing llm performance through answer synthesis. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6286–6303, 2025. [find](https://scholar.google.com/scholar?q=Bohan+Zhang%2C+Xiaokang+Zhang%2C+Jing+Zhang%2C+Jifan+Yu%2C+Sijia+Luo%2C+and+Jie+Tang%2E+Cot%2Dbased+synthesizer%3A+Enhancing+llm+performance+through+answer+synthesis%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+)
29. Zeyao Ma, Xiaokang Zhang, Jing Zhang, Jifan Yu, Sijia Luo, and Jie Tang. Dynamic scaling of unit tests for code reward modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6917–6935, 2025. [find](https://scholar.google.com/scholar?q=Zeyao+Ma%2C+Xiaokang+Zhang%2C+Jing+Zhang%2C+Jifan+Yu%2C+Sijia+Luo%2C+and+Jie+Tang%2E+Dynamic+scaling+of+unit+tests+for+code+reward+modeling%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Comput)
30. Jundong Xu, Hao Fei, Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, and Wynne Hsu. [Aristotle: Mastering logical reasoning with a logic-complete decompose-search-resolve framework](https://md.research.elamur.ai/free/en/papers/xu-2025-aristotle-mastering-logical-reasoning-logic/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Lingui…
31. Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, and Dongliang Xu. [Turning trash into treasure: Accelerating inference of large language models with token recycling](https://md.research.elamur.ai/free/en/papers/luo-2025-turning-trash-into-treasure-accelerating/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo…
32. Yiyao Yu, Yuxiang Zhang, Dongdong Zhang, Xiao Liang, Hengyuan Zhang, Xingxing Zhang, Mahmoud Khademi, Hany Hassan Awadalla, Junjie Wang, Yujiu Yang, et al. [Chain-of-reasoning: Towards unified mathematical reasoning in large language models via a multi-paradigm perspective](https://md.research.elamur.ai/free/en/papers/yu-2025-chain-reasoning-unified-mathematical-reasoning/). In Proceedings of the 63rd…
33. Yingchaojie Feng, Yiqun Sun, Yandong Sun, Minfeng Zhu, Qiang Huang, Anthony Kum Hoe Tung, and Wei Chen. Don’t reinvent the wheel: Efficient instruction-following text embedding based on guided space transformation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Yingchaojie+Feng%2C+Yiqun+Sun%2C+Yandong+Sun%2C+Minfeng+Zhu%2C+Qiang+Huang%2C+Anthony+Kum+Hoe+Tung%2C+and+Wei+Chen%2E+Don%E2%80%99t+reinvent+the+wheel%3A+Efficient+instruction%2Dfollowing+text+embedding+based+on+guided+space+t)
34. Yoav Gur-Arieh, Roy Mayan, Chen Agassy, Atticus Geiger, and Mor Geva. [Enhancing automated interpretability with output-centric feature descriptions](https://md.research.elamur.ai/free/en/papers/arieh-2025-enhancing-automated-interpretability-output-centric/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5757–5778, 2025.
35. Aili Chen, Chengyu Du, Jiangjie Chen, Jinghan Xu, Yikai Zhang, Siyu Yuan, Zulong Chen, Liangyue Li, and Yanghua Xiao. Deeper insight into your user: Directed persona refinement for dynamic persona modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Aili+Chen%2C+Chengyu+Du%2C+Jiangjie+Chen%2C+Jinghan+Xu%2C+Yikai+Zhang%2C+Siyu+Yuan%2C+Zulong+Chen%2C+Liangyue+Li%2C+and+Yanghua+Xiao%2E+Deeper+insight+into+your+user%3A+Directed+persona+refinement+for+dynamic+persona+mod)
36. Zhiyu Zhang, Wei Chen, Youfang Lin, and Huaiyu Wan. A generative adaptive replay continual learning model for temporal knowledge graph reasoning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10964–10977, 2025. [find](https://scholar.google.com/scholar?q=Zhiyu+Zhang%2C+Wei+Chen%2C+Youfang+Lin%2C+and+Huaiyu+Wan%2E+A+generative+adaptive+replay+continual+learning+model+for+temporal+knowledge+graph+reasoning%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Assoc)
37. Yumo Xu, Peng Qi, Jifan Chen, Kunlun Liu, Rujun Han, Lan Liu, Bonan Min, Vittorio Castelli, Arshit Gupta, and Zhiguo Wang. Citeeval: Principle-driven citation evaluation for source attribution. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… [find](https://scholar.google.com/scholar?q=Yumo+Xu%2C+Peng+Qi%2C+Jifan+Chen%2C+Kunlun+Liu%2C+Rujun+Han%2C+Lan+Liu%2C+Bonan+Min%2C+Vittorio+Castelli%2C+Arshit+Gupta%2C+and+Zhiguo+Wang%2E+Citeeval%3A+Principle%2Ddriven+citation+evaluation+for+source+attribution%2E+In+Pro)
38. Shahar Katz, Liran Ringel, Yaniv Romano, and Lior Wolf. Segment-based attention masking for gpts. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19308–19322, 2025. [find](https://scholar.google.com/scholar?q=Shahar+Katz%2C+Liran+Ringel%2C+Yaniv+Romano%2C+and+Lior+Wolf%2E+Segment%2Dbased+attention+masking+for+gpts%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+)
39. Shaobo Cui, Wenqing Liu, Yiyang Feng, Jiawei Zhou, and Boi Faltings. Conditional dichotomy quantification via geometric embedding. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7765–7791, 2025. [find](https://scholar.google.com/scholar?q=Shaobo+Cui%2C+Wenqing+Liu%2C+Yiyang+Feng%2C+Jiawei+Zhou%2C+and+Boi+Faltings%2E+Conditional+dichotomy+quantification+via+geometric+embedding%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Comp)
40. Wei Sun, Qianlong Du, Fuwei Cui, and Jiajun Zhang. [An efficient and precise training data construction framework for process-supervised reward model in mathematical reasoning](https://md.research.elamur.ai/free/en/papers/sun-2025-efficient-precise-training-data-construction/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 42…
41. Alan Sun. Circuit stability characterizes language model generalization. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9025–9040, 2025. [find](https://scholar.google.com/scholar?q=Alan+Sun%2E+Circuit+stability+characterizes+language+model+generalization%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pages+9025%E2%80%93)
42. Zijian Shao, Jiancan Wu, Weijian Chen, and Xiang Wang. Personal travel solver: A preference-driven llm-solver system for travel planning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 27622–27642, 2025. [find](https://scholar.google.com/scholar?q=Zijian+Shao%2C+Jiancan+Wu%2C+Weijian+Chen%2C+and+Xiang+Wang%2E+Personal+travel+solver%3A+A+preference%2Ddriven+llm%2Dsolver+system+for+travel+planning%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+f)
43. Peichao Lai, Zhengfeng Zhang, Wentao Zhang, Fangcheng Fu, and Bin Cui. Enhancing unsupervised sentence embeddings via knowledge-driven data augmentation and gaussian-decayed contrastive learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo… [find](https://scholar.google.com/scholar?q=Peichao+Lai%2C+Zhengfeng+Zhang%2C+Wentao+Zhang%2C+Fangcheng+Fu%2C+and+Bin+Cui%2E+Enhancing+unsupervised+sentence+embeddings+via+knowledge%2Ddriven+data+augmentation+and+gaussian%2Ddecayed+contrastive+learning%2E+In+P)
44. Georg Niess and Roman Kern. Ensemble watermarks for large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2903–2916, 2025. [find](https://scholar.google.com/scholar?q=Georg+Niess+and+Roman+Kern%2E+Ensemble+watermarks+for+large+language+models%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pages+290)
45. Chaoyi Xiang, Chunhua Liu, Simon De Deyne, and Lea Frermann. [Comparing moral values in western english-speaking societies and llms with word associations](https://md.research.elamur.ai/free/en/papers/xiang-2025-comparing-moral-values-western-english/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3521–3536, 2025.
46. Yizhu Jiao, Xuchao Zhang, Zhaoyang Wang, Yubo Ma, Zhun Deng, Rujia Wang, Chetan Bansal, Saravan Rajmohan, Jiawei Han, and Huaxiu Yao. Synergistic weak-strong collaboration by aligning preferences. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: L… [find](https://scholar.google.com/scholar?q=Yizhu+Jiao%2C+Xuchao+Zhang%2C+Zhaoyang+Wang%2C+Yubo+Ma%2C+Zhun+Deng%2C+Rujia+Wang%2C+Chetan+Bansal%2C+Saravan+Rajmohan%2C+Jiawei+Han%2C+and+Huaxiu+Yao%2E+Synergistic+weak%2Dstrong+collaboration+by+aligning+preferences%2E+In+)
47. Zhecheng Sheng, Xiruo Ding, Brian Hur, Changye Li, Trevor Cohen, and Serguei V. S. Pakhomov. Mitigating confounding in speech-based dementia detection through weight masking. In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, editors, Proceedings of the 63rd Annual Meeti… [find](https://scholar.google.com/scholar?q=Zhecheng+Sheng%2C+Xiruo+Ding%2C+Brian+Hur%2C+Changye+Li%2C+Trevor+Cohen%2C+and+Serguei+V%2E+S%2E+Pakhomov%2E+Mitigating+confounding+in+speech%2Dbased+dementia+detection+through+weight+masking%2E+In+Wanxiang+Che%2C+Joyce+Na)
48. Han Shu, Wenshuo Li, Yehui Tang, Yiman Zhang, Yihao Chen, Houqiang Li, Yunhe Wang, and Xinghao Chen. Tinysam: pushing the envelope for efficient segment anything model. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applicati… [find](https://scholar.google.com/scholar?q=Han+Shu%2C+Wenshuo+Li%2C+Yehui+Tang%2C+Yiman+Zhang%2C+Yihao+Chen%2C+Houqiang+Li%2C+Yunhe+Wang%2C+and+Xinghao+Chen%2E+Tinysam%3A+pushing+the+envelope+for+efficient+segment+anything+model%2E+In+Proceedings+of+the+Thirty%2DNi)
49. Peiyuan Liu, Hang Guo, Tao Dai, Naiqi Li, Jigang Bao, Xudong Ren, Yong Jiang, and Shu-Tao Xia. Calf: aligning llms for time series forecasting via cross-modal fine-tuning. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applic… [find](https://scholar.google.com/scholar?q=Peiyuan+Liu%2C+Hang+Guo%2C+Tao+Dai%2C+Naiqi+Li%2C+Jigang+Bao%2C+Xudong+Ren%2C+Yong+Jiang%2C+and+Shu%2DTao+Xia%2E+Calf%3A+aligning+llms+for+time+series+forecasting+via+cross%2Dmodal+fine%2Dtuning%2E+In+Proceedings+of+the+Thirty)
50. Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, Subhajit Chaudhury, Tejaswini Pedapati, Pierre Dognin, Keerthiram Murugesan, Erik Miehling, Martín Santillán Cooper, Kieran Fraser, Giulio Zizzo, Muhammad Zaid Hameed, Mark Purcell, Michael Desmond, Qian Pan, Inge Vejsbjerg, Elizabeth M. Daly,… [find](https://scholar.google.com/scholar?q=Inkit+Padhi%2C+Manish+Nagireddy%2C+Giandomenico+Cornacchia%2C+Subhajit+Chaudhury%2C+Tejaswini+Pedapati%2C+Pierre+Dognin%2C+Keerthiram+Murugesan%2C+Erik+Miehling%2C+Mart%C3%ADn+Santill%C3%A1n+Cooper%2C+Kieran+Fraser%2C+Giulio+Zizzo)
51. Jiaxin Gao, Qinglong Cao, and Yuntian Chen. Auto-regressive moving diffusion models for time series forecasting. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium o… [find](https://scholar.google.com/scholar?q=Jiaxin+Gao%2C+Qinglong+Cao%2C+and+Yuntian+Chen%2E+Auto%2Dregressive+moving+diffusion+models+for+time+series+forecasting%2E+In+Proceedings+of+the+Thirty%2DNinth+AAAI+Conference+on+Artificial+Intelligence+and+Thirt)
52. Artyom Stitsyuk and Jaesik Choi. xpatch: dual-stream time series forecasting with exponential seasonal-trend decomposition. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth… [find](https://scholar.google.com/scholar?q=Artyom+Stitsyuk+and+Jaesik+Choi%2E+xpatch%3A+dual%2Dstream+time+series+forecasting+with+exponential+seasonal%2Dtrend+decomposition%2E+In+Proceedings+of+the+Thirty%2DNinth+AAAI+Conference+on+Artificial+Intelligenc)
53. Chao Pang, Xingxing Weng, Jiang Wu, Jiayu Li, Yi Liu, Jiaxing Sun, Weijia Li, Shuai Wang, Litong Feng, Gui-Song Xia, and Conghui He. Vhm: versatile and honest vision language model for remote sensing image analysis. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Th… [find](https://scholar.google.com/scholar?q=Chao+Pang%2C+Xingxing+Weng%2C+Jiang+Wu%2C+Jiayu+Li%2C+Yi+Liu%2C+Jiaxing+Sun%2C+Weijia+Li%2C+Shuai+Wang%2C+Litong+Feng%2C+Gui%2DSong+Xia%2C+and+Conghui+He%2E+Vhm%3A+versatile+and+honest+vision+language+model+for+remote+sensing+)
54. Suhwan Cho, Seoung Wug Oh, Sangyoun Lee, and Joon-Young Lee. Elevating flow-guided video inpainting with reference generation. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteen… [find](https://scholar.google.com/scholar?q=Suhwan+Cho%2C+Seoung+Wug+Oh%2C+Sangyoun+Lee%2C+and+Joon%2DYoung+Lee%2E+Elevating+flow%2Dguided+video+inpainting+with+reference+generation%2E+In+Proceedings+of+the+Thirty%2DNinth+AAAI+Conference+on+Artificial+Intellig)
55. Yaxuan Kong, Zepu Wang, Yuqi Nie, Tian Zhou, Stefan Zohren, Yuxuan Liang, Peng Sun, and Qingsong Wen. Unlocking the power of lstm for long term time series forecasting. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applicati… [find](https://scholar.google.com/scholar?q=Yaxuan+Kong%2C+Zepu+Wang%2C+Yuqi+Nie%2C+Tian+Zhou%2C+Stefan+Zohren%2C+Yuxuan+Liang%2C+Peng+Sun%2C+and+Qingsong+Wen%2E+Unlocking+the+power+of+lstm+for+long+term+time+series+forecasting%2E+In+Proceedings+of+the+Thirty%2DNi)
56. HyunGi Kim, Siwon Kim, Jisoo Mok, and Sungroh Yoon. Battling the non-stationarity in time series forecasting via test-time adaptation. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and… [find](https://scholar.google.com/scholar?q=HyunGi+Kim%2C+Siwon+Kim%2C+Jisoo+Mok%2C+and+Sungroh+Yoon%2E+Battling+the+non%2Dstationarity+in+time+series+forecasting+via+test%2Dtime+adaptation%2E+In+Proceedings+of+the+Thirty%2DNinth+AAAI+Conference+on+Artificial+)
57. Ege Onur Taga, Muhammed Emrullah Ildiz, and Samet Oymak. Timepfn: effective multivariate time series forecasting with synthetic data. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and… [find](https://scholar.google.com/scholar?q=Ege+Onur+Taga%2C+Muhammed+Emrullah+Ildiz%2C+and+Samet+Oymak%2E+Timepfn%3A+effective+multivariate+time+series+forecasting+with+synthetic+data%2E+In+Proceedings+of+the+Thirty%2DNinth+AAAI+Conference+on+Artificial+I)
58. Landon Butler, Abhineet Agarwal, Justin Singh Kang, Yigit Efe Erginbas, Bin Yu, and Kannan Ramchandran. ProxySPEX: Inference-efficient interpretability via sparse feature interactions in LLMs. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Landon+Butler%2C+Abhineet+Agarwal%2C+Justin+Singh+Kang%2C+Yigit+Efe+Erginbas%2C+Bin+Yu%2C+and+Kannan+Ramchandran%2E+ProxySPEX%3A+Inference%2Defficient+interpretability+via+sparse+feature+interactions+in+LLMs%2E+In+The+)
59. Gleb Rodionov, Roman Garipov, Alina Shutova, George Yakushev, Erik Schultheis, Vage Egiazarian, Anton Sinitsin, Denis Kuznedelev, and Dan Alistarh. Hogwild! inference: Parallel LLM generation via concurrent attention. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 20… [find](https://scholar.google.com/scholar?q=Gleb+Rodionov%2C+Roman+Garipov%2C+Alina+Shutova%2C+George+Yakushev%2C+Erik+Schultheis%2C+Vage+Egiazarian%2C+Anton+Sinitsin%2C+Denis+Kuznedelev%2C+and+Dan+Alistarh%2E+Hogwild%21+inference%3A+Parallel+LLM+generation+via+conc)
60. Vahid Balazadeh, Hamidreza Kamkari, Valentin Thomas, Junwei Ma, Bingru Li, Jesse C. Cresswell, and Rahul Krishnan. CausalPFN: Amortized causal effect estimation via in-context learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Vahid+Balazadeh%2C+Hamidreza+Kamkari%2C+Valentin+Thomas%2C+Junwei+Ma%2C+Bingru+Li%2C+Jesse+C%2E+Cresswell%2C+and+Rahul+Krishnan%2E+CausalPFN%3A+Amortized+causal+effect+estimation+via+in%2Dcontext+learning%2E+In+The+Thirty%2D)
61. Seung Yul Lee, Hojoon Kim, Yutack Park, Dawoon Jeong, Seungwu Han, Yeonhong Park, and Jae W. Lee. FlashTP: Fused, sparsity-aware tensor product for machine learning interatomic potentials. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Seung+Yul+Lee%2C+Hojoon+Kim%2C+Yutack+Park%2C+Dawoon+Jeong%2C+Seungwu+Han%2C+Yeonhong+Park%2C+and+Jae+W%2E+Lee%2E+FlashTP%3A+Fused%2C+sparsity%2Daware+tensor+product+for+machine+learning+interatomic+potentials%2E+In+Forty%2Dse)
62. Weiwei Ye, Zhuopeng Xu, and Ning Gui. Non-stationary diffusion for probabilistic time series forecasting. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Weiwei+Ye%2C+Zhuopeng+Xu%2C+and+Ning+Gui%2E+Non%2Dstationary+diffusion+for+probabilistic+time+series+forecasting%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2C+2025%2E)
63. Xingjian Wu, Xiangfei Qiu, Hongfan Gao, Jilin Hu, Bin Yang, and Chenjuan Guo. $k^2$VAE: A koopman-kalman enhanced variational autoencoder for probabilistic time series forecasting. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Xingjian+Wu%2C+Xiangfei+Qiu%2C+Hongfan+Gao%2C+Jilin+Hu%2C+Bin+Yang%2C+and+Chenjuan+Guo%2E+%24k%5E2%24VAE%3A+A+koopman%2Dkalman+enhanced+variational+autoencoder+for+probabilistic+time+series+forecasting%2E+In+Forty%2Dsecond+Int)
64. Qihe Huang, Zhengyang Zhou, Kuo Yang, Zhongchao Yi, Xu Wang, and Yang Wang. Timebase: The power of minimalism in efficient long-term time series forecasting. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Qihe+Huang%2C+Zhengyang+Zhou%2C+Kuo+Yang%2C+Zhongchao+Yi%2C+Xu+Wang%2C+and+Yang+Wang%2E+Timebase%3A+The+power+of+minimalism+in+efficient+long%2Dterm+time+series+forecasting%2E+In+Forty%2Dsecond+International+Conference+o)
65. Yuchen Zhou, Jiamin Wu, Zichen Ren, Zhouheng Yao, Weiheng Lu, Kunyu Peng, Qihao Zheng, Chunfeng Song, Wanli Ouyang, and Chao Gou. Csbrain: A cross-scale spatiotemporal brain foundation model for eeg decoding. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Yuchen+Zhou%2C+Jiamin+Wu%2C+Zichen+Ren%2C+Zhouheng+Yao%2C+Weiheng+Lu%2C+Kunyu+Peng%2C+Qihao+Zheng%2C+Chunfeng+Song%2C+Wanli+Ouyang%2C+and+Chao+Gou%2E+Csbrain%3A+A+cross%2Dscale+spatiotemporal+brain+foundation+model+for+eeg+d)
66. Yuanhong Zhang, Muyao Yuan, Weizhan Zhang, Tieliang Gong, Wen Wen, Jiangyong Ying, and Weijie Shi. Infosam: fine-tuning the segment anything model from an information-theoretic perspective. In Proceedings of the 42nd International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Yuanhong+Zhang%2C+Muyao+Yuan%2C+Weizhan+Zhang%2C+Tieliang+Gong%2C+Wen+Wen%2C+Jiangyong+Ying%2C+and+Weijie+Shi%2E+Infosam%3A+fine%2Dtuning+the+segment+anything+model+from+an+information%2Dtheoretic+perspective%2E+In+Proceed)
67. Yingying Feng, Jie Li, Jie Hu, Yukang Zhang, Lei Tan, and Jiayi Ji. Mdreid: Modality-decoupled learning for any-to-any multi-modal object re-identification. Advances in Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Yingying+Feng%2C+Jie+Li%2C+Jie+Hu%2C+Yukang+Zhang%2C+Lei+Tan%2C+and+Jiayi+Ji%2E+Mdreid%3A+Modality%2Ddecoupled+learning+for+any%2Dto%2Dany+multi%2Dmodal+object+re%2Didentification%2E+Advances+in+Neural+Information+Processing+S)
68. Abdelrahman Eldesokey, Aleksandar Cvejić, Bernard Ghanem, and Peter Wonka. Mind-the-glitch: Visual correspondence for detecting inconsistencies in subject-driven generation. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Abdelrahman+Eldesokey%2C+Aleksandar+Cvejic%CC%81%2C+Bernard+Ghanem%2C+and+Peter+Wonka%2E+Mind%2Dthe%2Dglitch%3A+Visual+correspondence+for+detecting+inconsistencies+in+subject%2Ddriven+generation%2E+In+The+Thirty%2Dninth+Annua)
69. Yuxuan Yang, Dalin Zhang, Yuxuan Liang, Hua Lu, Gang Chen, and Huan Li. Not all data are good labels: On the self-supervised labeling for time series forecasting. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Yuxuan+Yang%2C+Dalin+Zhang%2C+Yuxuan+Liang%2C+Hua+Lu%2C+Gang+Chen%2C+and+Huan+Li%2E+Not+all+data+are+good+labels%3A+On+the+self%2Dsupervised+labeling+for+time+series+forecasting%2E+In+The+Thirty%2Dninth+Annual+Conference)
70. Xiong Zhang, Zhenli He, Changlong Fu, and Cheng Xie. Ia-ggad: Zero-shot generalist graph anomaly detection via invariant and affinity learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Xiong+Zhang%2C+Zhenli+He%2C+Changlong+Fu%2C+and+Cheng+Xie%2E+Ia%2Dggad%3A+Zero%2Dshot+generalist+graph+anomaly+detection+via+invariant+and+affinity+learning%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Informat)
71. Jiaxin Wang, Wenxuan Tu, and Jieren Cheng. Hierarchical shortest-path graph kernel network. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Jiaxin+Wang%2C+Wenxuan+Tu%2C+and+Jieren+Cheng%2E+Hierarchical+shortest%2Dpath+graph+kernel+network%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+2025%2E)
72. Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun, and Chenghao Liu. Visionts: visual masked autoencoders are free-lunch zero-shot time series forecasters. In Proceedings of the 42nd International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Mouxiang+Chen%2C+Lefei+Shen%2C+Zhuo+Li%2C+Xiaoyun+Joy+Wang%2C+Jianling+Sun%2C+and+Chenghao+Liu%2E+Visionts%3A+visual+masked+autoencoders+are+free%2Dlunch+zero%2Dshot+time+series+forecasters%2E+In+Proceedings+of+the+42nd+)
73. Kanghui Ning, Zijie Pan, Yu Liu, Yushan Jiang, James Y Zhang, Kashif Rasul, Anderson Schneider, Lintao Ma, Yuriy Nevmyvaka, and Dongjin Song. Ts-rag: Retrieval-augmented generation based time series foundation models are stronger zero-shot forecaster. In The Thirty-ninth Annual Conference on Neural… [find](https://scholar.google.com/scholar?q=Kanghui+Ning%2C+Zijie+Pan%2C+Yu+Liu%2C+Yushan+Jiang%2C+James+Y+Zhang%2C+Kashif+Rasul%2C+Anderson+Schneider%2C+Lintao+Ma%2C+Yuriy+Nevmyvaka%2C+and+Dongjin+Song%2E+Ts%2Drag%3A+Retrieval%2Daugmented+generation+based+time+series+f)
74. Zhiding Liu, Mingyue Cheng, GuanHao Zhao, Jiqian Yang, Qi Liu, and Enhong Chen. Improving time series forecasting via instance-aware post-hoc revision. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Zhiding+Liu%2C+Mingyue+Cheng%2C+GuanHao+Zhao%2C+Jiqian+Yang%2C+Qi+Liu%2C+and+Enhong+Chen%2E+Improving+time+series+forecasting+via+instance%2Daware+post%2Dhoc+revision%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+)
75. Arthur Deng, Karsten Householder, Fang Wu, K. Christopher Garcia, and Brian Trippe. Predicting mutational effects on protein binding from folding energy. In Proceedings of the 42nd International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Arthur+Deng%2C+Karsten+Householder%2C+Fang+Wu%2C+K%2E+Christopher+Garcia%2C+and+Brian+Trippe%2E+Predicting+mutational+effects+on+protein+binding+from+folding+energy%2E+In+Proceedings+of+the+42nd+International+Confe)
76. Baran Hashemi, Kurt Pasque, Chris Teska, and Ruriko Yoshida. Tropical attention: Neural algorithmic reasoning for combinatorial algorithms. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Baran+Hashemi%2C+Kurt+Pasque%2C+Chris+Teska%2C+and+Ruriko+Yoshida%2E+Tropical+attention%3A+Neural+algorithmic+reasoning+for+combinatorial+algorithms%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+)
77. Quan Zhou, Changhua Pei, Fei Sun, Jing Han, Zhengwei Gao, Haiming Zhang, Gaogang Xie, Dan Pei, and Jianhui Li. Kan-ad: time series anomaly detection with kolmogorov-arnold networks. In Proceedings of the 42nd International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Quan+Zhou%2C+Changhua+Pei%2C+Fei+Sun%2C+Jing+Han%2C+Zhengwei+Gao%2C+Haiming+Zhang%2C+Gaogang+Xie%2C+Dan+Pei%2C+and+Jianhui+Li%2E+Kan%2Dad%3A+time+series+anomaly+detection+with+kolmogorov%2Darnold+networks%2E+In+Proceedings+of+)
78. Hui He, Kun Yi, Yuanchi Ma, Qi Zhang, Zhendong Niu, and Guansong Pang. Sempo: Lightweight foundation models for time series forecasting. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Hui+He%2C+Kun+Yi%2C+Yuanchi+Ma%2C+Qi+Zhang%2C+Zhendong+Niu%2C+and+Guansong+Pang%2E+Sempo%3A+Lightweight+foundation+models+for+time+series+forecasting%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Pro)
79. Clement Benard. Tree ensemble explainability through the hoeffding functional decomposition and treehfd algorithm. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Clement+Benard%2E+Tree+ensemble+explainability+through+the+hoeffding+functional+decomposition+and+treehfd+algorithm%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+2025%2E)
80. Anastasia Koloskova, Youssef Allouah, Animesh Jha, Rachid Guerraoui, and Sanmi Koyejo. Certified unlearning for neural networks. In Proceedings of the 42nd International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Anastasia+Koloskova%2C+Youssef+Allouah%2C+Animesh+Jha%2C+Rachid+Guerraoui%2C+and+Sanmi+Koyejo%2E+Certified+unlearning+for+neural+networks%2E+In+Proceedings+of+the+42nd+International+Conference+on+Machine+Learning)
81. Yuanpei Gao, Qi Yan, Yan Leng, and Renjie Liao. Neural mjd: Neural non-stationary merton jump diffusion for time series prediction. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Yuanpei+Gao%2C+Qi+Yan%2C+Yan+Leng%2C+and+Renjie+Liao%2E+Neural+mjd%3A+Neural+non%2Dstationary+merton+jump+diffusion+for+time+series+prediction%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processi)
82. Yuhang Li, Tong Liu, Yangguang Cui, Ming Hu, and Xiaoqiang Li. One arrow, two hawks: Sharpness-aware minimization for federated learning via global model trajectory. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Yuhang+Li%2C+Tong+Liu%2C+Yangguang+Cui%2C+Ming+Hu%2C+and+Xiaoqiang+Li%2E+One+arrow%2C+two+hawks%3A+Sharpness%2Daware+minimization+for+federated+learning+via+global+model+trajectory%2E+In+ICML%2C+2025%2E)
83. Shengyu Feng and Yiming Yang. Regularized langevin dynamics for combinatorial optimization. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Shengyu+Feng+and+Yiming+Yang%2E+Regularized+langevin+dynamics+for+combinatorial+optimization%2E+In+ICML%2C+2025%2E)
84. Yvann Le Fay, Nicolas Chopin, and Simon Barthelmé. Least squares variational inference. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Yvann+Le+Fay%2C+Nicolas+Chopin%2C+and+Simon+Barthelm%C3%A9%2E+Least+squares+variational+inference%2E+In+NeurIPS%2C+2025%2E)
85. Viet-Hoang Tran, Thanh Tran, Thanh Chu, Tam Le, and Tan Nguyen. Tree-sliced entropy partial transport. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Viet%2DHoang+Tran%2C+Thanh+Tran%2C+Thanh+Chu%2C+Tam+Le%2C+and+Tan+Nguyen%2E+Tree%2Dsliced+entropy+partial+transport%2E+In+NeurIPS%2C+2025%2E)
86. Wenyu Zhu, Jianhui Wang, Bowen Gao, Yinjun Jia, Haichuan Tan, Ya-Qin Zhang, Wei-Ying Ma, and Yanyan Lan. Aanet: Virtual screening under structural uncertainty via alignment and aggregation. In Advances in Neural Information Processing Systems, 2025. [find](https://scholar.google.com/scholar?q=Wenyu+Zhu%2C+Jianhui+Wang%2C+Bowen+Gao%2C+Yinjun+Jia%2C+Haichuan+Tan%2C+Ya%2DQin+Zhang%2C+Wei%2DYing+Ma%2C+and+Yanyan+Lan%2E+Aanet%3A+Virtual+screening+under+structural+uncertainty+via+alignment+and+aggregation%2E+In+Advance)
87. Davide Sartor, Alberto Sinigaglia, and Gian Antonio Susto. Advancing constrained monotonic neural networks: Achieving universal approximation beyond bounded activations. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Davide+Sartor%2C+Alberto+Sinigaglia%2C+and+Gian+Antonio+Susto%2E+Advancing+constrained+monotonic+neural+networks%3A+Achieving+universal+approximation+beyond+bounded+activations%2E+In+ICML%2C+2025%2E)
88. Shuai Zhang, Chuan Zhou, Yang Liu, Peng Zhang, Xixun Lin, and Shirui Pan. Conformal anomaly detection in event sequences. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Shuai+Zhang%2C+Chuan+Zhou%2C+Yang+Liu%2C+Peng+Zhang%2C+Xixun+Lin%2C+and+Shirui+Pan%2E+Conformal+anomaly+detection+in+event+sequences%2E+In+ICML%2C+2025%2E)
89. Jonathan Scott, Christoph H. Lampert, and David Saulpic. Differentially private federated k-means clustering with server-side data. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Jonathan+Scott%2C+Christoph+H%2E+Lampert%2C+and+David+Saulpic%2E+Differentially+private+federated+k%2Dmeans+clustering+with+server%2Dside+data%2E+In+ICML%2C+2025%2E)
90. Yunze Tong, Fengda Zhang, Zihao Tang, Kaifeng Gao, Kai Huang, Pengfei Lyu, Jun Xiao, and Kun Kuang. Latent score-based reweighting for robust classification on imbalanced tabular data. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Yunze+Tong%2C+Fengda+Zhang%2C+Zihao+Tang%2C+Kaifeng+Gao%2C+Kai+Huang%2C+Pengfei+Lyu%2C+Jun+Xiao%2C+and+Kun+Kuang%2E+Latent+score%2Dbased+reweighting+for+robust+classification+on+imbalanced+tabular+data%2E+In+ICML%2C+2025%2E)
91. Zeyuan Ma, Zhiguang Cao, Zhou Jiang, Hongshu Guo, and Yue-Jiao Gong. Meta-black-box-optimization through offline q-function learning. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Zeyuan+Ma%2C+Zhiguang+Cao%2C+Zhou+Jiang%2C+Hongshu+Guo%2C+and+Yue%2DJiao+Gong%2E+Meta%2Dblack%2Dbox%2Doptimization+through+offline+q%2Dfunction+learning%2E+In+ICML%2C+2025%2E)
92. Fangzhou Wu and Sandeep Silwal. Efficient training-free online routing for high-volume multi-llm serving. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Fangzhou+Wu+and+Sandeep+Silwal%2E+Efficient+training%2Dfree+online+routing+for+high%2Dvolume+multi%2Dllm+serving%2E+In+NeurIPS%2C+2025%2E)
93. Maximilian Forstenhäusler, Daniel Külzer, Christos Anagnostopoulos, Shameem Puthiya Parambath, and Natascha Weber. Starformer: Semi-supervised task-informed representation learning via dynamic attention-based regional masking for sequential data. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Maximilian+Forstenh%C3%A4usler%2C+Daniel+K%C3%BClzer%2C+Christos+Anagnostopoulos%2C+Shameem+Puthiya+Parambath%2C+and+Natascha+Weber%2E+Starformer%3A+Semi%2Dsupervised+task%2Dinformed+representation+learning+via+dynamic+attenti)
94. Xinyu Li, Yuchen Luo, Hao Wang, Haoxuan Li, Liuhua Peng, Feng Liu, Yandong Guo, Kun Zhang, and Mingming Gong. Towards accurate time series forecasting via implicit decoding. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Xinyu+Li%2C+Yuchen+Luo%2C+Hao+Wang%2C+Haoxuan+Li%2C+Liuhua+Peng%2C+Feng+Liu%2C+Yandong+Guo%2C+Kun+Zhang%2C+and+Mingming+Gong%2E+Towards+accurate+time+series+forecasting+via+implicit+decoding%2E+In+NeurIPS%2C+2025%2E)
95. Mélodie Monod, Alessandro Micheli, and Samir Bhatt. Neuralsurv: Deep survival analysis with bayesian uncertainty quantification. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=M%C3%A9lodie+Monod%2C+Alessandro+Micheli%2C+and+Samir+Bhatt%2E+Neuralsurv%3A+Deep+survival+analysis+with+bayesian+uncertainty+quantification%2E+In+NeurIPS%2C+2025%2E)
96. Yisong Fu, Fei Wang, Zezhi Shao, Boyu Diao, Lin Wu, Zhulin An, Chengqing Yu, Yujie Li, and Yongjun Xu. On the integration of spatial-temporal knowledge: A lightweight approach to atmospheric time series forecasting. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Yisong+Fu%2C+Fei+Wang%2C+Zezhi+Shao%2C+Boyu+Diao%2C+Lin+Wu%2C+Zhulin+An%2C+Chengqing+Yu%2C+Yujie+Li%2C+and+Yongjun+Xu%2E+On+the+integration+of+spatial%2Dtemporal+knowledge%3A+A+lightweight+approach+to+atmospheric+time+seri)
97. Yuxin Pan, Zhiguang Cao, Chengyang GU, Liu Liu, Peilin Zhao, Yize Chen, and Fangzhen Lin. Multi-task vehicle routing solver via mixture of specialized experts under state-decomposable mdp. In NeurIPS, 2025. [find](https://scholar.google.com/scholar?q=Yuxin+Pan%2C+Zhiguang+Cao%2C+Chengyang+GU%2C+Liu+Liu%2C+Peilin+Zhao%2C+Yize+Chen%2C+and+Fangzhen+Lin%2E+Multi%2Dtask+vehicle+routing+solver+via+mixture+of+specialized+experts+under+state%2Ddecomposable+mdp%2E+In+NeurIPS%2C)
98. Seunghan Lee, Taeyoung Park, and Kibok Lee. Channel normalization for time series channel identification. In ICML, 2025. [find](https://scholar.google.com/scholar?q=Seunghan+Lee%2C+Taeyoung+Park%2C+and+Kibok+Lee%2E+Channel+normalization+for+time+series+channel+identification%2E+In+ICML%2C+2025%2E)
99. Johnny Xi, Hugh Dance, Peter Orbanz, and Benjamin Bloem-Reddy. Distinguishing cause from effect with causal velocity models. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Johnny+Xi%2C+Hugh+Dance%2C+Peter+Orbanz%2C+and+Benjamin+Bloem%2DReddy%2E+Distinguishing+cause+from+effect+with+causal+velocity+models%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2C+2025%2E)
100. Min Chen, Guansong Pang, Wenjun Wang, and Cheng Yan. Information bottleneck-guided MLPs for robust spatial-temporal forecasting. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Min+Chen%2C+Guansong+Pang%2C+Wenjun+Wang%2C+and+Cheng+Yan%2E+Information+bottleneck%2Dguided+MLPs+for+robust+spatial%2Dtemporal+forecasting%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2C+2025%2E)
101. Zhuo He, Shuang Li, Wenze Song, Longhui Yuan, Jian Liang, Han Li, and Kun Gai. Learning time-aware causal representation for model generalization in evolving domains. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Zhuo+He%2C+Shuang+Li%2C+Wenze+Song%2C+Longhui+Yuan%2C+Jian+Liang%2C+Han+Li%2C+and+Kun+Gai%2E+Learning+time%2Daware+causal+representation+for+model+generalization+in+evolving+domains%2E+In+Forty%2Dsecond+International+Con)
102. Mingyi Li, Michael R. Metel, and Akiko Takeda. Modified k-means algorithm with local optimality guarantees. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Mingyi+Li%2C+Michael+R%2E+Metel%2C+and+Akiko+Takeda%2E+Modified+k%2Dmeans+algorithm+with+local+optimality+guarantees%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2C+2025%2E)
103. Tianle Li, Yongzhi Huang, Linshan Jiang, Chang Liu, Qipeng Xie, Wenfeng Du, Lu Wang, and Kaishun Wu. FedWMSAM: Fast and flat federated learning via weighted momentum and sharpness-aware minimization. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Tianle+Li%2C+Yongzhi+Huang%2C+Linshan+Jiang%2C+Chang+Liu%2C+Qipeng+Xie%2C+Wenfeng+Du%2C+Lu+Wang%2C+and+Kaishun+Wu%2E+FedWMSAM%3A+Fast+and+flat+federated+learning+via+weighted+momentum+and+sharpness%2Daware+minimization%2E+)
104. Dongmin Bang, Inyoung Sung, Yinhua Piao, Sangseon Lee, and Sun Kim. Boundr.e: Predicting drug-likeness via biomedical knowledge alignment and EM-like one-class boundary optimization. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Dongmin+Bang%2C+Inyoung+Sung%2C+Yinhua+Piao%2C+Sangseon+Lee%2C+and+Sun+Kim%2E+Boundr%2Ee%3A+Predicting+drug%2Dlikeness+via+biomedical+knowledge+alignment+and+EM%2Dlike+one%2Dclass+boundary+optimization%2E+In+Forty%2Dsecond+I)
105. Zihao Tang, Boyuan Wang, Chuan Wen, and Jiaye Teng. Accelerating feature conformal prediction via taylor approximation. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Zihao+Tang%2C+Boyuan+Wang%2C+Chuan+Wen%2C+and+Jiaye+Teng%2E+Accelerating+feature+conformal+prediction+via+taylor+approximation%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+)
106. Jinseong Park, Yujin Choi, and Jaewook Lee. Multi-class support vector machine with differential privacy. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Jinseong+Park%2C+Yujin+Choi%2C+and+Jaewook+Lee%2E+Multi%2Dclass+support+vector+machine+with+differential+privacy%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+2026%2E)
107. Kaicheng Zhang, Sinian Zhang, Doudou Zhou, and Yidong Zhou. Wasserstein transfer learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Kaicheng+Zhang%2C+Sinian+Zhang%2C+Doudou+Zhou%2C+and+Yidong+Zhou%2E+Wasserstein+transfer+learning%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+2026%2E)
108. Tong Wei, Bo-Lin Wang, Jiang-Xin Shi, Yu-Feng Li, and Min-Ling Zhang. X-mahalanobis: Transformer feature mixing for reliable OOD detection. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Tong+Wei%2C+Bo%2DLin+Wang%2C+Jiang%2DXin+Shi%2C+Yu%2DFeng+Li%2C+and+Min%2DLing+Zhang%2E+X%2Dmahalanobis%3A+Transformer+feature+mixing+for+reliable+OOD+detection%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+)
109. Kijung Jeon, Michael Muehlebach, and Molei Tao. Fast non-log-concave sampling under nonconvex equality and inequality constraints with landing. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Kijung+Jeon%2C+Michael+Muehlebach%2C+and+Molei+Tao%2E+Fast+non%2Dlog%2Dconcave+sampling+under+nonconvex+equality+and+inequality+constraints+with+landing%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Informat)
110. Hao Wang, zhengnan li, Zhichao Chen, Xu Chen, Shuting He, Guangyi Liu, Haoxuan Li, and Zhouchen Lin. Iterative missing data imputation with model form adaptation and non-missing feature supervision. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Hao+Wang%2C+zhengnan+li%2C+Zhichao+Chen%2C+Xu+Chen%2C+Shuting+He%2C+Guangyi+Liu%2C+Haoxuan+Li%2C+and+Zhouchen+Lin%2E+Iterative+missing+data+imputation+with+model+form+adaptation+and+non%2Dmissing+feature+supervision%2E+I)
111. Arman Behnam and Binghui Wang. Measure-theoretic anti-causal representation learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Arman+Behnam+and+Binghui+Wang%2E+Measure%2Dtheoretic+anti%2Dcausal+representation+learning%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+2026%2E)
112. Zhichao Zhu, YANG QI, Hengyuan Ma, Wenlian Lu, and Jianfeng Feng. Stochastic forward-forward learning through representational dimensionality compression. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Zhichao+Zhu%2C+YANG+QI%2C+Hengyuan+Ma%2C+Wenlian+Lu%2C+and+Jianfeng+Feng%2E+Stochastic+forward%2Dforward+learning+through+representational+dimensionality+compression%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neur)
113. Haifeng Wen, Hong Xing, and Osvaldo Simeone. Distributed conformal prediction via message passing. In Forty-second International Conference on Machine Learning, 2025. [find](https://scholar.google.com/scholar?q=Haifeng+Wen%2C+Hong+Xing%2C+and+Osvaldo+Simeone%2E+Distributed+conformal+prediction+via+message+passing%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2C+2025%2E)
114. Boyu Chen, Zhixiang Zhou, Liuhua Peng, and Zhonglei Wang. Balanced active inference. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Boyu+Chen%2C+Zhixiang+Zhou%2C+Liuhua+Peng%2C+and+Zhonglei+Wang%2E+Balanced+active+inference%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+Systems%2C+2026%2E)
115. Gerardo Flores, Alyssa Hasegawa Smith, Julia Fukuyama, and Ashia C. Wilson. Aligning evaluation with clinical priorities: Calibration, label shift, and error costs. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2026. [find](https://scholar.google.com/scholar?q=Gerardo+Flores%2C+Alyssa+Hasegawa+Smith%2C+Julia+Fukuyama%2C+and+Ashia+C%2E+Wilson%2E+Aligning+evaluation+with+clinical+priorities%3A+Calibration%2C+label+shift%2C+and+error+costs%2E+In+The+Thirty%2Dninth+Annual+Conferen)
116. Barret Zoph and Quoc V Le. [Neural architecture search with reinforcement learning](https://md.research.elamur.ai/free/en/papers/zoph-2016-neural-architecture-search-reinforcement-learning/). arXiv preprint arXiv:1611.01578, 2016.
117. Esteban Real, Alok Aggarwal, Yanping Huang, and Quoc V Le. Regularized evolution for image classifier architecture search. In Proceedings of the aaai conference on artificial intelligence, volume 33, pages 4780–4789, 2019. [find](https://scholar.google.com/scholar?q=Esteban+Real%2C+Alok+Aggarwal%2C+Yanping+Huang%2C+and+Quoc+V+Le%2E+Regularized+evolution+for+image+classifier+architecture+search%2E+In+Proceedings+of+the+aaai+conference+on+artificial+intelligence%2C+volume+33%2C+)
118. Yu Shang, Yu Li, Fengli Xu, and Yong Li. Synergy-of-thoughts: Eliciting efficient reasoning in hybrid language models. arXiv preprint arXiv:2402.02563, 2024. [find](https://scholar.google.com/scholar?q=Yu+Shang%2C+Yu+Li%2C+Fengli+Xu%2C+and+Yong+Li%2E+Synergy%2Dof%2Dthoughts%3A+Eliciting+efficient+reasoning+in+hybrid+language+models%2E+arXiv+preprint+arXiv%3A2402%2E02563%2C+2024%2E)
119. Hanxiao Liu, Karen Simonyan, and Yiming Yang. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055, 2018. [find](https://scholar.google.com/scholar?q=Hanxiao+Liu%2C+Karen+Simonyan%2C+and+Yiming+Yang%2E+Darts%3A+Differentiable+architecture+search%2E+arXiv+preprint+arXiv%3A1806%2E09055%2C+2018%2E)
120. John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. [Swe-agent: Agent-computer interfaces enable automated software engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/). Advances in Neural Information Processing Systems, 37:50528–50652, 2024.
121. Yu Shang, Yu Li, Keyu Zhao, Likai Ma, Jiahe Liu, Fengli Xu, and Yong Li. Agentsquare: Automatic llm agent search in modular design space. arXiv preprint arXiv:2410.06153, 2024. — [arXiv:2410.06153](https://arxiv.org/abs/2410.06153) [find](https://scholar.google.com/scholar?q=Yu+Shang%2C+Yu+Li%2C+Keyu+Zhao%2C+Likai+Ma%2C+Jiahe+Liu%2C+Fengli+Xu%2C+and+Yong+Li%2E+Agentsquare%3A+Automatic+llm+agent+search+in+modular+design+space%2E+arXiv+preprint+arXiv%3A2410%2E06153%2C+2024%2E+%E2%80%94+%5BarXiv%3A2410%2E06153%5D%28ht)
122. Yu Li, Lehui Li, Zhihao Wu, Qingmin Liao, Jianye Hao, Kun Shao, and Fengli Xu. Agentswift: Efficient llm agent design via value-guided hierarchical search. In Proceedings of the AAAI Conference on Artificial Intelligence, 2026. [find](https://scholar.google.com/scholar?q=Yu+Li%2C+Lehui+Li%2C+Zhihao+Wu%2C+Qingmin+Liao%2C+Jianye+Hao%2C+Kun+Shao%2C+and+Fengli+Xu%2E+Agentswift%3A+Efficient+llm+agent+design+via+value%2Dguided+hierarchical+search%2E+In+Proceedings+of+the+AAAI+Conference+on+Art)
123. Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M Pawan Kumar, Emilien Dupont, Francisco JR Ruiz, Jordan S Ellenberg, Pengming Wang, Omar Fawzi, et al. [Mathematical discoveries from program search with large language models](https://md.research.elamur.ai/free/en/papers/paredes-2023-mathematical-discoveries-program-search-large/). Nature, 625(7995):468–475, 2024.
124. Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, and Anima Anandkumar. [Eureka: Human-level reward design via coding large language models](https://md.research.elamur.ai/free/en/papers/ma-2023-eureka-human-level-reward-design/). arXiv preprint arXiv:2310.12931, 2023.
125. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. [The ai scientist: Towards fully automated open-ended scientific discovery](https://md.research.elamur.ai/free/en/papers/lu-2024-ai-scientist-fully-automated/). arXiv preprint arXiv:2408.06292, 2024.
126. Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shengran Hu, Chris Lu, Jakob Foerster, Jeff Clune, and David Ha. [The ai scientist-v2: Workshop-level automated scientific discovery via agentic tree search](https://md.research.elamur.ai/free/en/papers/yamada-2025-ai-scientist-v2-workshop/). arXiv preprint arXiv:2504.08066, 2025.
127. Juraj Gottweis, Wei-Hung Weng, Alexander Daryin, Tao Tu, Anil Palepu, Petar Sirkovic, Artiom Myaskovsky, Felix Weissenberger, Keran Rong, Ryutaro Tanno, et al. Towards an ai co-scientist. arXiv preprint arXiv:2502.[18864, 2025](https://md.research.elamur.ai/free/en/papers/gottweis-2025-accelerating-scientific-discovery-co/).
128. Yixuan Weng, Minjun Zhu, Qiujie Xie, Qiyao Sun, Zhen Lin, Sifan Liu, and Yue Zhang. Deepscientist: Advancing frontier-pushing scientific findings progressively. arXiv preprint arXiv:2509.26603, 2025. [find](https://scholar.google.com/scholar?q=Yixuan+Weng%2C+Minjun+Zhu%2C+Qiujie+Xie%2C+Qiyao+Sun%2C+Zhen+Lin%2C+Sifan+Liu%2C+and+Yue+Zhang%2E+Deepscientist%3A+Advancing+frontier%2Dpushing+scientific+findings+progressively%2E+arXiv+preprint+arXiv%3A2509%2E26603%2C+2025%2E)
129. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. [Researchagent: Iterative research idea generation over scientific literature with large language models](https://md.research.elamur.ai/free/en/papers/baek-2024-researchagent-iterative-research-idea/). In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics…

*Updated 2 November 2026*