---
title: "ArrowGEV — paper by Yu et al. (2026) — summary and ideas"
description: "The authors argue that current Vision Language Models learn to link events to timestamps only in normally played videos, so… 84 references."
authors: ["Fangxu Yu", "Ziyao Lu", "Liqiang Niu", "Fandong Meng", "Jie Zhou"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1730/"
doi: "10.18653/v1/2026.findings-acl.1730"
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/yu-2026-arrowgev-grounding-events-video-learning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2026-arrowgev-grounding-events-video-learning/)

[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/23/) / ArrowGEV: Grounding Events in Video via Learning the Arrow of Time

# ArrowGEV: Grounding Events in Video via Learning the Arrow of Time

**Authors:** Fangxu Yu, Ziyao Lu, Liqiang Niu, [Fandong Meng](https://md.research.elamur.ai/free/en/authors/fandong-meng/) and [Jie Zhou](https://md.research.elamur.ai/free/en/authors/jie-zhou/) · **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.1730/) · [PDF](https://aclanthology.org/2026.findings-acl.1730.pdf) · [DOI 10.18653/v1/2026.findings-acl.1730](https://doi.org/10.18653/v1/2026.findings-acl.1730) · [OpenAlex](https://openalex.org/W7166863747)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper addresses video event grounding (GEV): finding the time span in an untrimmed video that matches a text description. The authors argue that current Vision Language Models learn to link events to timestamps only in normally played videos, so they ignore which way time flows. A pilot study with Qwen2.5-VL-7B supports this: the model still "finds" direction-dependent actions in reversed clips where those actions no longer occur. ArrowGEV is a GRPO-based reinforcement learning framework that draws on the physics idea of the arrow of time. It splits events into two types:
- **Time-sensitive** events change meaning when reversed. For these, the model is rewarded for telling forward and backward videos apart.
- **Time-insensitive** events keep their meaning. For these, the model is rewarded for grounding them consistently in both directions.

A difficulty-aware scheme up-weights hard samples and uses a curriculum to filter out already-solved ones. ArrowGEV beats the base model and RL baselines on Charades-STA, ActivityNet and TVGBench, improves recognition of temporal direction, and helps out-of-distribution video understanding and reasoning.

## Key points
- On Qwen2.5-VL-7B, mIoU improves from 38.3 to 54.1 on Charades-STA, 25.2 to 39.9 on ActivityNet, and 17.8 to 29.2 on TVGBench.
- In the ablation, the temporal reward adds roughly 4–6% in R1@m over vanilla GRPO. Weight adjustment and filtering each bring further gains.
- Plain GRPO alone already lifts the base VLM by about 10–30% on the grounding benchmarks.
- With a 3B backbone, ArrowGEV-3B reaches mIoU of 42.3, 24.3 and 20.3 on Charades-STA, ActivityNet and TVGBench. It beats both Qwen-2.5-VL-3B and Time-R1-3B.
- A temporal directionality discrepancy (TDD) metric shows a clearer forward/backward distinction for time-sensitive events and more consistent grounding for time-insensitive ones. The authors note the method's high compute cost as a limitation.

*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

- [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) — Company, Shenzhen, China · 163 works · 21,032 citations
- [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) — University, Nanjing, China · 99 works · 8,512 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Fangxu Yu, Ziyao Lu, Liqiang Niu, Fandong Meng and Jie Zhou. 2026. ArrowGEV: Grounding Events in Video via Learning the Arrow of Time. 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{yu2026arrowgev,
  title = {{ArrowGEV: Grounding Events in Video via Learning the Arrow of Time}},
  author = {Fangxu Yu, Ziyao Lu, Liqiang Niu, Fandong Meng and Jie Zhou},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1730},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1730}
}
```

- [← previous ARQA: A Benchmark for Grounded Table–Text QA in Enterprise Annual Reports](https://md.research.elamur.ai/free/en/papers/wang-2026-arqa-benchmark-grounded-table-text/)
- [next → Artful Writing, Authentic Emotions: Distinguishing Human-Written from LLM-Generated Metaphors by Annotation and Classification](https://md.research.elamur.ai/free/en/papers/regneri-2026-artful-writing-authentic-emotions-distinguishing/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/)

## References

84 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Lisa Anne Hendricks, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, and Bryan Russell. 2017. Localizing moments in video with natural language. In Proceedings of the IEEE international conference on computer vision, pages 5803–5812. [find](https://scholar.google.com/scholar?q=Lisa+Anne+Hendricks%2C+Oliver+Wang%2C+Eli+Shechtman%2C+Josef+Sivic%2C+Trevor+Darrell%2C+and+Bryan+Russell%2E+2017%2E+Localizing+moments+in+video+with+natural+language%2E+In+Proceedings+of+the+IEEE+international+confe)
2. Y Alp Aslandogan and Clement T. Yu. 2002. Techniques and systems for image and video retrieval. IEEE transactions on Knowledge and Data Engineering, 11(1):56–63. [find](https://scholar.google.com/scholar?q=Y+Alp+Aslandogan+and+Clement+T%2E+Yu%2E+2002%2E+Techniques+and+systems+for+image+and+video+retrieval%2E+IEEE+transactions+on+Knowledge+and+Data+Engineering%2C+11%281%29%3A56%E2%80%9363%2E)
3. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. [Qwen2.5-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). arXiv preprint arXiv:25…
4. Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, and Juan Carlos Niebles. 2015. Activitynet: A large-scale video benchmark for human activity understanding. In Proceedings of the ieee conference on computer vision and pattern recognition, pages 961–970. [find](https://scholar.google.com/scholar?q=Fabian+Caba+Heilbron%2C+Victor+Escorcia%2C+Bernard+Ghanem%2C+and+Juan+Carlos+Niebles%2E+2015%2E+Activitynet%3A+A+large%2Dscale+video+benchmark+for+human+activity+understanding%2E+In+Proceedings+of+the+ieee+conference)
5. Huiyi Chen, Jiawei Peng, Dehai Min, Changchang Sun, Kaijie Chen, Yan Yan, Xu Yang, and Lu Cheng. 2025a. Mvi-bench: A comprehensive benchmark for evaluating robustness to misleading visual inputs in lvlms. arXiv preprint arXiv:2511.14159. — [arXiv:2511.14159](https://arxiv.org/abs/2511.14159) [find](https://scholar.google.com/scholar?q=Huiyi+Chen%2C+Jiawei+Peng%2C+Dehai+Min%2C+Changchang+Sun%2C+Kaijie+Chen%2C+Yan+Yan%2C+Xu+Yang%2C+and+Lu+Cheng%2E+2025a%2E+Mvi%2Dbench%3A+A+comprehensive+benchmark+for+evaluating+robustness+to+misleading+visual+inputs+in+lv)
6. Ruizhe Chen, Zhiting Fan, Tianze Luo, Heqing Zou, Zhaopeng Feng, Guiyang Xie, Hansheng Zhang, Zhuochen Wang, Zuozhu Liu, and Huaijian Zhang. 2025b. Datasets and recipes for video temporal grounding via reinforcement learning. arXiv preprint arXiv:2507.18100. [find](https://scholar.google.com/scholar?q=Ruizhe+Chen%2C+Zhiting+Fan%2C+Tianze+Luo%2C+Heqing+Zou%2C+Zhaopeng+Feng%2C+Guiyang+Xie%2C+Hansheng+Zhang%2C+Zhuochen+Wang%2C+Zuozhu+Liu%2C+and+Huaijian+Zhang%2E+2025b%2E+Datasets+and+recipes+for+video+temporal+grounding+vi)
7. Yi-Wen Chen, Yi-Hsuan Tsai, and Ming-Hsuan Yang. 2021. End-to-end multi-modal video temporal grounding. Advances in Neural Information Processing Systems, 34:28442–28453. [find](https://scholar.google.com/scholar?q=Yi%2DWen+Chen%2C+Yi%2DHsuan+Tsai%2C+and+Ming%2DHsuan+Yang%2E+2021%2E+End%2Dto%2Dend+multi%2Dmodal+video+temporal+grounding%2E+Advances+in+Neural+Information+Processing+Systems%2C+34%3A28442%E2%80%9328453%2E)
8. Yukang Chen, Wei Huang, Baifeng Shi, Qinghao Hu, Hanrong Ye, Ligeng Zhu, Zhijian Liu, Pavlo Molchanov, Jan Kautz, Xiaojuan Qi, and 1 others. 2025c. Scaling rl to long videos. arXiv preprint arXiv:2507.07966. [find](https://scholar.google.com/scholar?q=Yukang+Chen%2C+Wei+Huang%2C+Baifeng+Shi%2C+Qinghao+Hu%2C+Hanrong+Ye%2C+Ligeng+Zhu%2C+Zhijian+Liu%2C+Pavlo+Molchanov%2C+Jan+Kautz%2C+Xiaojuan+Qi%2C+and+1+others%2E+2025c%2E+Scaling+rl+to+long+videos%2E+arXiv+preprint+arXiv%3A2507)
9. Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V Le, Sergey Levine, and Yi Ma. 2025. [Sft memorizes, rl generalizes: A comparative study of foundation model post-training](https://md.research.elamur.ai/free/en/papers/chu-2025-sft-memorizes-rl-generalizes-comparative/). arXiv preprint arXiv:2501.17161.
10. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). arX…
11. Yang Du, Yuqi Liu, and Qin Jin. 2024. Reversed in time: A novel temporal-emphasized benchmark for cross-modal video-text retrieval. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 5260–5269. [find](https://scholar.google.com/scholar?q=Yang+Du%2C+Yuqi+Liu%2C+and+Qin+Jin%2E+2024%2E+Reversed+in+time%3A+A+novel+temporal%2Demphasized+benchmark+for+cross%2Dmodal+video%2Dtext+retrieval%2E+In+Proceedings+of+the+32nd+ACM+International+Conference+on+Multimedi)
12. Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman. 2019. Temporal cycle-consistency learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1801–1810. [find](https://scholar.google.com/scholar?q=Debidatta+Dwibedi%2C+Yusuf+Aytar%2C+Jonathan+Tompson%2C+Pierre+Sermanet%2C+and+Andrew+Zisserman%2E+2019%2E+Temporal+cycle%2Dconsistency+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pat)
13. Arthur Eddington. 2019. The nature of the physical world: THE GIFFORD LECTURES 1927, volume 23. BoD–Books on Demand. [find](https://scholar.google.com/scholar?q=Arthur+Eddington%2E+2019%2E+The+nature+of+the+physical+world%3A+THE+GIFFORD+LECTURES+1927%2C+volume+23%2E+BoD%E2%80%93Books+on+Demand%2E)
14. Kaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Benyou Wang, and Xiangyu Yue. 2025. Video-r1: Reinforcing video reasoning in mllms. arXiv preprint arXiv:2503.21776. — [arXiv:2503.21776](https://arxiv.org/abs/2503.21776) [find](https://scholar.google.com/scholar?q=Kaituo+Feng%2C+Kaixiong+Gong%2C+Bohao+Li%2C+Zonghao+Guo%2C+Yibing+Wang%2C+Tianshuo+Peng%2C+Benyou+Wang%2C+and+Xiangyu+Yue%2E+2025%2E+Video%2Dr1%3A+Reinforcing+video+reasoning+in+mllms%2E+arXiv+preprint+arXiv%3A2503%2E21776%2E+%E2%80%94+%5Ba)
15. Chaoyou Fu, Yuhan Dai, Yongdong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, and 1 others. 2024. [Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis](https://md.research.elamur.ai/free/en/papers/fu-2024-video-mme-first-ever-comprehensive/). arXiv preprint arXiv:2405.21075.
16. Valentin Gabeur, Chen Sun, Karteek Alahari, and Cordelia Schmid. 2020. Multi-modal transformer for video retrieval. In European Conference on Computer Vision, pages 214–229. Springer. [find](https://scholar.google.com/scholar?q=Valentin+Gabeur%2C+Chen+Sun%2C+Karteek+Alahari%2C+and+Cordelia+Schmid%2E+2020%2E+Multi%2Dmodal+transformer+for+video+retrieval%2E+In+European+Conference+on+Computer+Vision%2C+pages+214%E2%80%93229%2E+Springer%2E)
17. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025a. Deepseekr1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633–638. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Peiyi+Wang%2C+Qihao+Zhu%2C+Runxin+Xu%2C+Ruoyu+Zhang%2C+Shirong+Ma%2C+Xiao+Bi%2C+and+1+others%2E+2025a%2E+Deepseekr1+incentivizes+reasoning+in+llms+through+reinforcem)
18. Jarvis Guo, Tuney Zheng, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Yizhi Li, Graham Neubig, Wenhu Chen, and Xiang Yue. 2024a. [Mammoth-vl: Eliciting multimodal reasoning with instruction tuning at scale](https://md.research.elamur.ai/free/en/papers/guo-2025-mammoth-vl-eliciting-multimodal-reasoning/). arXiv preprint arXiv:2412.05237.
19. Yongxin Guo, Jingyu Liu, Mingda Li, Dingxin Cheng, Xiaoying Tang, Dianbo Sui, Qingbin Liu, Xi Chen, and Kevin Zhao. 2025b. Vtg-llm: Integrating timestamp knowledge into video llms for enhanced video temporal grounding. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, page… [find](https://scholar.google.com/scholar?q=Yongxin+Guo%2C+Jingyu+Liu%2C+Mingda+Li%2C+Dingxin+Cheng%2C+Xiaoying+Tang%2C+Dianbo+Sui%2C+Qingbin+Liu%2C+Xi+Chen%2C+and+Kevin+Zhao%2E+2025b%2E+Vtg%2Dllm%3A+Integrating+timestamp+knowledge+into+video+llms+for+enhanced+video+t)
20. Yongxin Guo, Jingyu Liu, Mingda Li, Qingbin Liu, Xi Chen, and Xiaoying Tang. 2024b. Trace: Temporal grounding video llm via causal event modeling. arXiv preprint arXiv:2410.05643. — [arXiv:2410.05643](https://arxiv.org/abs/2410.05643) [find](https://scholar.google.com/scholar?q=Yongxin+Guo%2C+Jingyu+Liu%2C+Mingda+Li%2C+Qingbin+Liu%2C+Xi+Chen%2C+and+Xiaoying+Tang%2E+2024b%2E+Trace%3A+Temporal+grounding+video+llm+via+causal+event+modeling%2E+arXiv+preprint+arXiv%3A2410%2E05643%2E+%E2%80%94+%5BarXiv%3A2410%2E05643%5D)
21. Tanveer Hannan, Md Mohaiminul Islam, Thomas Seidl, and Gedas Bertasius. 2024. Rgnet: A unified clip retrieval and grounding network for long videos. In European Conference on Computer Vision, pages 352–369. Springer. [find](https://scholar.google.com/scholar?q=Tanveer+Hannan%2C+Md+Mohaiminul+Islam%2C+Thomas+Seidl%2C+and+Gedas+Bertasius%2E+2024%2E+Rgnet%3A+A+unified+clip+retrieval+and+grounding+network+for+long+videos%2E+In+European+Conference+on+Computer+Vision%2C+pages+35)
22. Wenyi Hong, Weihan Wang, Ming Ding, Wenmeng Yu, Qingsong Lv, Yan Wang, Yean Cheng, Shiyu Huang, Junhui Ji, Zhao Xue, and 1 others. 2024. [Cogvlm2: Visual language models for image and video understanding](https://md.research.elamur.ai/free/en/papers/hong-2024-cogvlm2-visual-language-models/). arXiv preprint arXiv:2408.16500.
23. Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing-Kwong Chan, Chong-Wah Ngo, Zheng Shou, and Nan Duan. 2022. Cone: An efficient coarse-to-fine alignment framework for long video temporal grounding. arXiv preprint arXiv:2209.10918. [find](https://scholar.google.com/scholar?q=Zhijian+Hou%2C+Wanjun+Zhong%2C+Lei+Ji%2C+Difei+Gao%2C+Kun+Yan%2C+Wing%2DKwong+Chan%2C+Chong%2DWah+Ngo%2C+Zheng+Shou%2C+and+Nan+Duan%2E+2022%2E+Cone%3A+An+efficient+coarse%2Dto%2Dfine+alignment+framework+for+long+video+temporal+gro)
24. Kairui Hu, Penghao Wu, Fanyi Pu, Wang Xiao, Yuanhan Zhang, Xiang Yue, Bo Li, and Ziwei Liu. 2025. Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos. arXiv preprint arXiv:2501.13826. — [arXiv:2501.13826](https://arxiv.org/abs/2501.13826) [find](https://scholar.google.com/scholar?q=Kairui+Hu%2C+Penghao+Wu%2C+Fanyi+Pu%2C+Wang+Xiao%2C+Yuanhan+Zhang%2C+Xiang+Yue%2C+Bo+Li%2C+and+Ziwei+Liu%2E+2025%2E+Video%2Dmmmu%3A+Evaluating+knowledge+acquisition+from+multi%2Ddiscipline+professional+videos%2E+arXiv+preprint)
25. Bin Huang, Xin Wang, Hong Chen, Zihan Song, and Wenwu Zhu. 2024a. Vtimellm: Empower llm to grasp video moments. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14271–14280. [find](https://scholar.google.com/scholar?q=Bin+Huang%2C+Xin+Wang%2C+Hong+Chen%2C+Zihan+Song%2C+and+Wenwu+Zhu%2E+2024a%2E+Vtimellm%3A+Empower+llm+to+grasp+video+moments%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+pa)
26. De-An Huang, Shijia Liao, Subhashree Radhakrishnan, Hongxu Yin, Pavlo Molchanov, Zhiding Yu, and Jan Kautz. 2024b. Lita: Language instructed temporal-localization assistant. In European Conference on Computer Vision, pages 202–218. Springer. [find](https://scholar.google.com/scholar?q=De%2DAn+Huang%2C+Shijia+Liao%2C+Subhashree+Radhakrishnan%2C+Hongxu+Yin%2C+Pavlo+Molchanov%2C+Zhiding+Yu%2C+and+Jan+Kautz%2E+2024b%2E+Lita%3A+Language+instructed+temporal%2Dlocalization+assistant%2E+In+European+Conference+on+)
27. Vladimir Iashin and Esa Rahtu. 2020. Multi-modal dense video captioning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 958–959. [find](https://scholar.google.com/scholar?q=Vladimir+Iashin+and+Esa+Rahtu%2E+2020%2E+Multi%2Dmodal+dense+video+captioning%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+recognition+workshops%2C+pages+958%E2%80%93959%2E)
28. Jinhyun Jang, Jungin Park, Jin Kim, Hyeongjun Kwon, and Kwanghoon Sohn. 2023. Knowing where to focus: Event-aware transformer for video grounding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13846–13856. [find](https://scholar.google.com/scholar?q=Jinhyun+Jang%2C+Jungin+Park%2C+Jin+Kim%2C+Hyeongjun+Kwon%2C+and+Kwanghoon+Sohn%2E+2023%2E+Knowing+where+to+focus%3A+Event%2Daware+transformer+for+video+grounding%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conferen)
29. Mingyu Jeon, Sunjae Yoon, Jonghee Kim, and Junyeong Kim. 2026. Granalign: Granularity-aware alignment framework for zero-shot video moment retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 5287–5295. [find](https://scholar.google.com/scholar?q=Mingyu+Jeon%2C+Sunjae+Yoon%2C+Jonghee+Kim%2C+and+Junyeong+Kim%2E+2026%2E+Granalign%3A+Granularity%2Daware+alignment+framework+for+zero%2Dshot+video+moment+retrieval%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificia)
30. Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, and Seong Tae Kim. 2024. Do you remember? dense video captioning with cross-modal memory retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13894–13904. [find](https://scholar.google.com/scholar?q=Minkuk+Kim%2C+Hyeon+Bae+Kim%2C+Jinyoung+Moon%2C+Jinwoo+Choi%2C+and+Seong+Tae+Kim%2E+2024%2E+Do+you+remember%3F+dense+video+captioning+with+cross%2Dmodal+memory+retrieval%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+)
31. Yogesh Kulkarni and Pooyan Fazli. 2025. Avatar: Reinforcement learning to see, hear, and reason over video. arXiv preprint arXiv:2508.03100. — [arXiv:2508.03100](https://arxiv.org/abs/2508.03100) [find](https://scholar.google.com/scholar?q=Yogesh+Kulkarni+and+Pooyan+Fazli%2E+2025%2E+Avatar%3A+Reinforcement+learning+to+see%2C+hear%2C+and+reason+over+video%2E+arXiv+preprint+arXiv%3A2508%2E03100%2E+%E2%80%94+%5BarXiv%3A2508%2E03100%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2508%2E03100%29)
32. David Layzer. 1975. The arrow of time. Scientific American, 233(6):56–69. [find](https://scholar.google.com/scholar?q=David+Layzer%2E+1975%2E+The+arrow+of+time%2E+Scientific+American%2C+233%286%29%3A56%E2%80%9369%2E)
33. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and 1 others. 2024a. [Llava-onevision: Easy visual task transfer](https://md.research.elamur.ai/free/en/papers/li-2024-llava-onevision-easy-visual-task/). arXiv preprint arXiv:2408.03326.
34. Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, and 1 others. 2024b. [Mvbench: A comprehensive multi-modal video understanding benchmark](https://md.research.elamur.ai/free/en/papers/li-2023-mvbench-comprehensive-multi-modal-video/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22195–22206.
35. Xinhao Li, Yi Wang, Jiashuo Yu, Xiangyu Zeng, Yuhan Zhu, Haian Huang, Jianfei Gao, Kunchang Li, Yinan He, Chenting Wang, Yu Qiao, Yali Wang, and Limin Wang. 2024c. Videochat-flash: Hierarchical compression for long-context video modeling. arXiv preprint arXiv:2501.00574. — [arXiv:2501.00574](https://arxiv.org/abs/2501.00574) [find](https://scholar.google.com/scholar?q=Xinhao+Li%2C+Yi+Wang%2C+Jiashuo+Yu%2C+Xiangyu+Zeng%2C+Yuhan+Zhu%2C+Haian+Huang%2C+Jianfei+Gao%2C+Kunchang+Li%2C+Yinan+He%2C+Chenting+Wang%2C+Yu+Qiao%2C+Yali+Wang%2C+and+Limin+Wang%2E+2024c%2E+Videochat%2Dflash%3A+Hierarchical+compre)
36. Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, and Limin Wang. 2020. Tea: Temporal excitation and aggregation for action recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 909–918. [find](https://scholar.google.com/scholar?q=Yan+Li%2C+Bin+Ji%2C+Xintian+Shi%2C+Jianguo+Zhang%2C+Bin+Kang%2C+and+Limin+Wang%2E+2020%2E+Tea%3A+Temporal+excitation+and+aggregation+for+action+recognition%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+visio)
37. Zeqian Li, Shangzhe Di, Zhonghua Zhai, Weilin Huang, Yanfeng Wang, and Weidi Xie. 2025. Universal video temporal grounding with generative multi-modal large language models. arXiv preprint arXiv:2506.18883. — [arXiv:2506.18883](https://arxiv.org/abs/2506.18883) [find](https://scholar.google.com/scholar?q=Zeqian+Li%2C+Shangzhe+Di%2C+Zhonghua+Zhai%2C+Weilin+Huang%2C+Yanfeng+Wang%2C+and+Weidi+Xie%2E+2025%2E+Universal+video+temporal+grounding+with+generative+multi%2Dmodal+large+language+models%2E+arXiv+preprint+arXiv%3A2506%2E)
38. Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, Yiqing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Van Tu Vu, and 1 others. 2024d. Groundinggpt: Language enhanced multi-modal grounding model. arXiv preprint arXiv:2401.06071. [find](https://scholar.google.com/scholar?q=Zhaowei+Li%2C+Qi+Xu%2C+Dong+Zhang%2C+Hang+Song%2C+Yiqing+Cai%2C+Qi+Qi%2C+Ran+Zhou%2C+Junting+Pan%2C+Zefeng+Li%2C+Van+Tu+Vu%2C+and+1+others%2E+2024d%2E+Groundinggpt%3A+Language+enhanced+multi%2Dmodal+grounding+model%2E+arXiv+prepri)
39. Kevin Qinghong Lin, Pengchuan Zhang, Joya Chen, Shraman Pramanick, Difei Gao, Alex Jinpeng Wang, Rui Yan, and Mike Zheng Shou. 2023. Univtg: Towards unified video-language temporal grounding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2794–2804. [find](https://scholar.google.com/scholar?q=Kevin+Qinghong+Lin%2C+Pengchuan+Zhang%2C+Joya+Chen%2C+Shraman+Pramanick%2C+Difei+Gao%2C+Alex+Jinpeng+Wang%2C+Rui+Yan%2C+and+Mike+Zheng+Shou%2E+2023%2E+Univtg%3A+Towards+unified+video%2Dlanguage+temporal+grounding%2E+In+Proce)
40. Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, Lei Li, Sishuo Chen, Xu Sun, and Lu Hou. 2024. Tempcompass: Do video llms really understand videos? arXiv preprint arXiv:2403.00476. [find](https://scholar.google.com/scholar?q=Yuanxin+Liu%2C+Shicheng+Li%2C+Yi+Liu%2C+Yuxiang+Wang%2C+Shuhuai+Ren%2C+Lei+Li%2C+Sishuo+Chen%2C+Xu+Sun%2C+and+Lu+Hou%2E+2024%2E+Tempcompass%3A+Do+video+llms+really+understand+videos%3F+arXiv+preprint+arXiv%3A2403%2E00476%2E)
41. Ziyang Luo, Haoning Wu, Dongxu Li, Jing Ma, Mohan Kankanhalli, and Junnan Li. 2025. Videoautoarena: An automated arena for evaluating large multimodal models in video analysis through user simulation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 8461–8474. [find](https://scholar.google.com/scholar?q=Ziyang+Luo%2C+Haoning+Wu%2C+Dongxu+Li%2C+Jing+Ma%2C+Mohan+Kankanhalli%2C+and+Junnan+Li%2E+2025%2E+Videoautoarena%3A+An+automated+arena+for+evaluating+large+multimodal+models+in+video+analysis+through+user+simulation%2E)
42. Willi Menapace, Aliaksandr Siarohin, Ivan Skorokhodov, Ekaterina Deyneka, Tsai-Shien Chen, Anil Kag, Yuwei Fang, Aleksei Stoliar, Elisa Ricci, Jian Ren, and 1 others. 2024. Snap video: Scaled spatiotemporal transformers for text-to-video synthesis. In Proceedings of the IEEE/CVF Conference on Comput… [find](https://scholar.google.com/scholar?q=Willi+Menapace%2C+Aliaksandr+Siarohin%2C+Ivan+Skorokhodov%2C+Ekaterina+Deyneka%2C+Tsai%2DShien+Chen%2C+Anil+Kag%2C+Yuwei+Fang%2C+Aleksei+Stoliar%2C+Elisa+Ricci%2C+Jian+Ren%2C+and+1+others%2E+2024%2E+Snap+video%3A+Scaled+spatiote)
43. Fanqing Meng, Lingxiao Du, Zongkai Liu, Zhixiang Zhou, Quanfeng Lu, Daocheng Fu, Tiancheng Han, Botian Shi, Wenhai Wang, Junjun He, and 1 others. 2025. Mm-eureka: Exploring the frontiers of multimodal reasoning with rule-based reinforcement learning. arXiv preprint arXiv:2503.07365. [find](https://scholar.google.com/scholar?q=Fanqing+Meng%2C+Lingxiao+Du%2C+Zongkai+Liu%2C+Zhixiang+Zhou%2C+Quanfeng+Lu%2C+Daocheng+Fu%2C+Tiancheng+Han%2C+Botian+Shi%2C+Wenhai+Wang%2C+Junjun+He%2C+and+1+others%2E+2025%2E+Mm%2Deureka%3A+Exploring+the+frontiers+of+multimodal)
44. Ishan Misra, C Lawrence Zitnick, and Martial Hebert. 2016. Shuffle and learn: unsupervised learning using temporal order verification. In Computer Vision– ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pages 527–544. Springer. [find](https://scholar.google.com/scholar?q=Ishan+Misra%2C+C+Lawrence+Zitnick%2C+and+Martial+Hebert%2E+2016%2E+Shuffle+and+learn%3A+unsupervised+learning+using+temporal+order+verification%2E+In+Computer+Vision%E2%80%93+ECCV+2016%3A+14th+European+Conference%2C+Amsterda)
45. Fangzhou Mu, Sicheng Mo, and Yin Li. 2024a. Snag: Scalable and accurate video grounding. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 18930–18940. [find](https://scholar.google.com/scholar?q=Fangzhou+Mu%2C+Sicheng+Mo%2C+and+Yin+Li%2E+2024a%2E+Snag%3A+Scalable+and+accurate+video+grounding%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+recognition%2C+pages+18930%E2%80%9318940%2E)
46. Fangzhou Mu, Sicheng Mo, and Yin Li. 2024b. Snag: Scalable and accurate video grounding. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 18930–18940. [find](https://scholar.google.com/scholar?q=Fangzhou+Mu%2C+Sicheng+Mo%2C+and+Yin+Li%2E+2024b%2E+Snag%3A+Scalable+and+accurate+video+grounding%2E+2024+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+pages+18930%E2%80%9318940%2E)
47. Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, and Wei Lu. 2021. Interventional video grounding with dual contrastive learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2765– 2775. [find](https://scholar.google.com/scholar?q=Guoshun+Nan%2C+Rui+Qiao%2C+Yao+Xiao%2C+Jun+Liu%2C+Sicong+Leng%2C+Hao+Zhang%2C+and+Wei+Lu%2E+2021%2E+Interventional+video+grounding+with+dual+contrastive+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer)
48. Thong Thanh Nguyen, Yi Bin, Xiaobao Wu, Zhiyuan Hu, Cong-Duy T Nguyen, See-Kiong Ng, and Anh Tuan Luu. 2025. Multi-scale contrastive learning for video temporal grounding. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 6227–6235. [find](https://scholar.google.com/scholar?q=Thong+Thanh+Nguyen%2C+Yi+Bin%2C+Xiaobao+Wu%2C+Zhiyuan+Hu%2C+Cong%2DDuy+T+Nguyen%2C+See%2DKiong+Ng%2C+and+Anh+Tuan+Luu%2E+2025%2E+Multi%2Dscale+contrastive+learning+for+video+temporal+grounding%2E+In+Proceedings+of+the+AAAI+C)
49. Andreea-Maria Oncescu, Joao F Henriques, Yang Liu, Andrew Zisserman, and Samuel Albanie. 2021. Queryd: A video dataset with high-quality text and audio narrations. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2265–2269. IEEE. [find](https://scholar.google.com/scholar?q=Andreea%2DMaria+Oncescu%2C+Joao+F+Henriques%2C+Yang+Liu%2C+Andrew+Zisserman%2C+and+Samuel+Albanie%2E+2021%2E+Queryd%3A+A+video+dataset+with+high%2Dquality+text+and+audio+narrations%2E+In+ICASSP+2021%2D2021+IEEE+Internation)
50. Yulin Pan, Xiangteng He, Biao Gong, Yiliang Lv, Yujun Shen, Yuxin Peng, and Deli Zhao. 2023. Scanning only once: An end-to-end framework for fast temporal grounding in long videos. In Proceedings of the IEEE/CVF international conference on computer vision, pages 13767–13777. [find](https://scholar.google.com/scholar?q=Yulin+Pan%2C+Xiangteng+He%2C+Biao+Gong%2C+Yiliang+Lv%2C+Yujun+Shen%2C+Yuxin+Peng%2C+and+Deli+Zhao%2E+2023%2E+Scanning+only+once%3A+An+end%2Dto%2Dend+framework+for+fast+temporal+grounding+in+long+videos%2E+In+Proceedings+of+t)
51. Yingzhe Peng, Gongrui Zhang, Miaosen Zhang, Zhiyuan You, Jie Liu, Qipeng Zhu, Kai Yang, Xingzhong Xu, Xin Geng, and Xu Yang. 2025. Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl. arXiv preprint arXiv:2503.07536. — [arXiv:2503.07536](https://arxiv.org/abs/2503.07536) [find](https://scholar.google.com/scholar?q=Yingzhe+Peng%2C+Gongrui+Zhang%2C+Miaosen+Zhang%2C+Zhiyuan+You%2C+Jie+Liu%2C+Qipeng+Zhu%2C+Kai+Yang%2C+Xingzhong+Xu%2C+Xin+Geng%2C+and+Xu+Yang%2E+2025%2E+Lmm%2Dr1%3A+Empowering+3b+lmms+with+strong+reasoning+abilities+through+tw)
52. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, and 1 others. 2025. [Openai gpt-5 system card](https://md.research.elamur.ai/free/en/papers/singh-2025-openai-gpt-5-system-card/). arXiv preprint arXiv:2601.03267.
53. Alex Su, Haozhe Wang, Weiming Ren, Fangzhen Lin, and Wenhu Chen. 2025. Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning. arXiv preprint arXiv:2505.15966. — [arXiv:2505.15966](https://arxiv.org/abs/2505.15966) [find](https://scholar.google.com/scholar?q=Alex+Su%2C+Haozhe+Wang%2C+Weiming+Ren%2C+Fangzhen+Lin%2C+and+Wenhu+Chen%2E+2025%2E+Pixel+reasoner%3A+Incentivizing+pixel%2Dspace+reasoning+with+curiosity%2Ddriven+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2505%2E15966)
54. Zhenxiong Tan, Xingyi Yang, Songhua Liu, and Xinchao Wang. 2024. Video-infinity: Distributed long video generation. arXiv preprint arXiv:2406.16260. [find](https://scholar.google.com/scholar?q=Zhenxiong+Tan%2C+Xingyi+Yang%2C+Songhua+Liu%2C+and+Xinchao+Wang%2E+2024%2E+Video%2Dinfinity%3A+Distributed+long+video+generation%2E+arXiv+preprint+arXiv%3A2406%2E16260%2E)
55. Kwai Keye Team, Biao Yang, Bin Wen, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, and 1 others. 2025. Kwai keye-vl technical report. arXiv preprint arXiv:2507.01949. — [arXiv:2507.01949](https://arxiv.org/abs/2507.01949) [find](https://scholar.google.com/scholar?q=Kwai+Keye+Team%2C+Biao+Yang%2C+Bin+Wen%2C+Changyi+Liu%2C+Chenglong+Chu%2C+Chengru+Song%2C+Chongling+Rao%2C+Chuan+Yi%2C+Da+Li%2C+Dunju+Zang%2C+and+1+others%2E+2025%2E+Kwai+keye%2Dvl+technical+report%2E+arXiv+preprint+arXiv%3A2507%2E0)
56. Shulin Tian, Ruiqi Wang, Hongming Guo, Penghao Wu, Yuhao Dong, Xiuying Wang, Jingkang Yang, Hao Zhang, Hongyuan Zhu, and Ziwei Liu. 2025. Ego-r1: Chain-of-tool-thought for ultra-long egocentric video reasoning. arXiv preprint arXiv:2506.13654. — [arXiv:2506.13654](https://arxiv.org/abs/2506.13654) [find](https://scholar.google.com/scholar?q=Shulin+Tian%2C+Ruiqi+Wang%2C+Hongming+Guo%2C+Penghao+Wu%2C+Yuhao+Dong%2C+Xiuying+Wang%2C+Jingkang+Yang%2C+Hao+Zhang%2C+Hongyuan+Zhu%2C+and+Ziwei+Liu%2E+2025%2E+Ego%2Dr1%3A+Chain%2Dof%2Dtool%2Dthought+for+ultra%2Dlong+egocentric+video+)
57. Will Price and Dima Damen. 2019. Retro-actions: Learning’close’by time-reversing’open’videos. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pages 0–0. [find](https://scholar.google.com/scholar?q=Will+Price+and+Dima+Damen%2E+2019%2E+Retro%2Dactions%3A+Learning%E2%80%99close%E2%80%99by+time%2Dreversing%E2%80%99open%E2%80%99videos%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conference+on+Computer+Vision+Workshops%2C+pages+0%E2%80%930%2E)
58. Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, and Luc Van Gool. 2018. Temporal segment networks for action recognition in videos. IEEE transactions on pattern analysis and machine intelligence, 41(11):2740–2755. [find](https://scholar.google.com/scholar?q=Limin+Wang%2C+Yuanjun+Xiong%2C+Zhe+Wang%2C+Yu+Qiao%2C+Dahua+Lin%2C+Xiaoou+Tang%2C+and+Luc+Van+Gool%2E+2018%2E+Temporal+segment+networks+for+action+recognition+in+videos%2E+IEEE+transactions+on+pattern+analysis+and+mach)
59. Long Qian, Juncheng Li, Yu Wu, Yaobo Ye, Hao Fei, Tat-Seng Chua, Yueting Zhuang, and Siliang Tang. 2024. Momentor: Advancing video large language model with fine-grained temporal reasoning. arXiv preprint arXiv:2402.11435. — [arXiv:2402.11435](https://arxiv.org/abs/2402.11435) [find](https://scholar.google.com/scholar?q=Long+Qian%2C+Juncheng+Li%2C+Yu+Wu%2C+Yaobo+Ye%2C+Hao+Fei%2C+Tat%2DSeng+Chua%2C+Yueting+Zhuang%2C+and+Siliang+Tang%2E+2024%2E+Momentor%3A+Advancing+video+large+language+model+with+fine%2Dgrained+temporal+reasoning%2E+arXiv+prep)
60. Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, and 1 others. 2025a. [Internvl3](https://md.research.elamur.ai/free/en/papers/wang-2025-internvl3-5-advancing-open/). 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265.
61. Mengxue Qu, Xiaodong Chen, Wu Liu, Alicia Li, and Yao Zhao. 2024. Chatvtg: Video temporal grounding via chat with video dialogue large language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1847–1856. [find](https://scholar.google.com/scholar?q=Mengxue+Qu%2C+Xiaodong+Chen%2C+Wu+Liu%2C+Alicia+Li%2C+and+Yao+Zhao%2E+2024%2E+Chatvtg%3A+Video+temporal+grounding+via+chat+with+video+dialogue+large+language+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Com)
62. Ye Wang, Ziheng Wang, Boshen Xu, Yang Du, Kejun Lin, Zihan Xiao, Zihao Yue, Jianzhong Ju, Liang Zhang, Dingyi Yang, and 1 others. 2025b. Time-r1: Post-training large vision language model for temporal video grounding. arXiv preprint arXiv:2503.13377. — [arXiv:2503.13377](https://arxiv.org/abs/2503.13377) [find](https://scholar.google.com/scholar?q=Ye+Wang%2C+Ziheng+Wang%2C+Boshen+Xu%2C+Yang+Du%2C+Kejun+Lin%2C+Zihan+Xiao%2C+Zihao+Yue%2C+Jianzhong+Ju%2C+Liang+Zhang%2C+Dingyi+Yang%2C+and+1+others%2E+2025b%2E+Time%2Dr1%3A+Post%2Dtraining+large+vision+language+model+for+temporal)
63. Shuhuai Ren, Linli Yao, Shicheng Li, Xu Sun, and Lu Hou. 2024. Timechat: A time-sensitive multimodal large language model for long video understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14313–14323. [find](https://scholar.google.com/scholar?q=Shuhuai+Ren%2C+Linli+Yao%2C+Shicheng+Li%2C+Xu+Sun%2C+and+Lu+Hou%2E+2024%2E+Timechat%3A+A+time%2Dsensitive+multimodal+large+language+model+for+long+video+understanding%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Com)
64. Yueqian Wang, Xiaojun Meng, Jianxin Liang, Yuxuan Wang, Qun Liu, and Dongyan Zhao. 2024. Hawkeye: Training video-text llms for grounding text in videos. [find](https://scholar.google.com/scholar?q=Yueqian+Wang%2C+Xiaojun+Meng%2C+Jianxin+Liang%2C+Yuxuan+Wang%2C+Qun+Liu%2C+and+Dongyan+Zhao%2E+2024%2E+Hawkeye%3A+Training+video%2Dtext+llms+for+grounding+text+in+videos%2E)
65. Paul Hongsuck Seo, Arsha Nagrani, Anurag Arnab, and Cordelia Schmid. 2022. End-to-end generative pre-training for multimodal video captioning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17959–17968. [find](https://scholar.google.com/scholar?q=Paul+Hongsuck+Seo%2C+Arsha+Nagrani%2C+Anurag+Arnab%2C+and+Cordelia+Schmid%2E+2022%2E+End%2Dto%2Dend+generative+pre%2Dtraining+for+multimodal+video+captioning%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vis)
66. Gunnar A Sigurdsson, Gül Varol, Xiaolong Wang, Ali Farhadi, Ivan Laptev, and Abhinav Gupta. 2016. Hollywood in homes: Crowdsourcing data collection for activity understanding. In Proceedings of the European Conference on Computer Vision (ECCV). [find](https://scholar.google.com/scholar?q=Gunnar+A+Sigurdsson%2C+G%C3%BCl+Varol%2C+Xiaolong+Wang%2C+Ali+Farhadi%2C+Ivan+Laptev%2C+and+Abhinav+Gupta%2E+2016%2E+Hollywood+in+homes%3A+Crowdsourcing+data+collection+for+activity+understanding%2E+In+Proceedings+of+the+Eu)
67. Donglai Wei, Joseph J Lim, Andrew Zisserman, and William T Freeman. 2018. Learning and using the arrow of time. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8052–8060. [find](https://scholar.google.com/scholar?q=Donglai+Wei%2C+Joseph+J+Lim%2C+Andrew+Zisserman%2C+and+William+T+Freeman%2E+2018%2E+Learning+and+using+the+arrow+of+time%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+pages+)
68. Jongbhin Woo, Hyeonggon Ryu, Youngjoon Jang, Jae Won Cho, and Joon Son Chung. 2024. Let me finish my sentence: Video temporal grounding with holistic text understanding. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 8199–8208. [find](https://scholar.google.com/scholar?q=Jongbhin+Woo%2C+Hyeonggon+Ryu%2C+Youngjoon+Jang%2C+Jae+Won+Cho%2C+and+Joon+Son+Chung%2E+2024%2E+Let+me+finish+my+sentence%3A+Video+temporal+grounding+with+holistic+text+understanding%2E+In+Proceedings+of+the+32nd+ACM)
69. LLM-Core-Team Xiaomi. 2025. [Mimo-vl technical report](https://md.research.elamur.ai/free/en/papers/team-2025-llm-mimo-vl-technical-report/). Preprint, arXiv:2506.03569.
70. Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, and Christoph Feichtenhofer. 2021. Videoclip: Contrastive pre-training for zero-shot video-text understanding. arXiv preprint arXiv:2109.14084. [find](https://scholar.google.com/scholar?q=Hu+Xu%2C+Gargi+Ghosh%2C+Po%2DYao+Huang%2C+Dmytro+Okhonko%2C+Armen+Aghajanyan%2C+Florian+Metze%2C+Luke+Zettlemoyer%2C+and+Christoph+Feichtenhofer%2E+2021%2E+Videoclip%3A+Contrastive+pre%2Dtraining+for+zero%2Dshot+video%2Dtext+und)
71. Zihui Xue, Mi Luo, and Kristen Grauman. 2025. Seeing the arrow of time in large multimodal models. ArXiv, abs/2506.03340. — [arXiv:2506.03340](https://arxiv.org/abs/2506.03340) [find](https://scholar.google.com/scholar?q=Zihui+Xue%2C+Mi+Luo%2C+and+Kristen+Grauman%2E+2025%2E+Seeing+the+arrow+of+time+in+large+multimodal+models%2E+ArXiv%2C+abs%2F2506%2E03340%2E+%E2%80%94+%5BarXiv%3A2506%2E03340%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E03340%29)
72. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, and 1 others. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+and+1+others%2E+2024%2E+Qwen2%2E+5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115)
73. Haolin Yang, Feilong Tang, Ming Hu, Qingyu Yin, Yulong Li, Yexin Liu, Zelin Peng, Peng Gao, Junjun He, Zongyuan Ge, and 1 others. 2025a. Scalingnoise: Scaling inference-time search for generating infinite videos. arXiv preprint arXiv:2503.16400. — [arXiv:2503.16400](https://arxiv.org/abs/2503.16400) [find](https://scholar.google.com/scholar?q=Haolin+Yang%2C+Feilong+Tang%2C+Ming+Hu%2C+Qingyu+Yin%2C+Yulong+Li%2C+Yexin+Liu%2C+Zelin+Peng%2C+Peng+Gao%2C+Junjun+He%2C+Zongyuan+Ge%2C+and+1+others%2E+2025a%2E+Scalingnoise%3A+Scaling+inference%2Dtime+search+for+generating+infi)
74. Yilun Zhao, Haowei Zhang, Lujing Xie, Tongyan Hu, Guo Gan, Yitao Long, Zhiyuan Hu, Weiyuan Chen, Chuhan Li, Zhijian Xu, and 1 others. 2025. Mmvu: Measuring expert-level multi-discipline video understanding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 8475–8489. [find](https://scholar.google.com/scholar?q=Yilun+Zhao%2C+Haowei+Zhang%2C+Lujing+Xie%2C+Tongyan+Hu%2C+Guo+Gan%2C+Yitao+Long%2C+Zhiyuan+Hu%2C+Weiyuan+Chen%2C+Chuhan+Li%2C+Zhijian+Xu%2C+and+1+others%2E+2025%2E+Mmvu%3A+Measuring+expert%2Dlevel+multi%2Ddiscipline+video+understa)
75. Yue Zhao, Yuanjun Xiong, Limin Wang, Zhirong Wu, Xiaoou Tang, and Dahua Lin. 2017. Temporal action detection with structured segment networks. In Proceedings of the IEEE international conference on computer vision, pages 2914–2923. [find](https://scholar.google.com/scholar?q=Yue+Zhao%2C+Yuanjun+Xiong%2C+Limin+Wang%2C+Zhirong+Wu%2C+Xiaoou+Tang%2C+and+Dahua+Lin%2E+2017%2E+Temporal+action+detection+with+structured+segment+networks%2E+In+Proceedings+of+the+IEEE+international+conference+on+co)
76. Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, and Zeyu Xiong. 2022. Rethinking the video sampling and reasoning strategies for temporal sentence grounding. In Findings of the Association for Computational Linguistics: EMNLP 2022. [find](https://scholar.google.com/scholar?q=Jiahao+Zhu%2C+Daizong+Liu%2C+Pan+Zhou%2C+Xing+Di%2C+Yu+Cheng%2C+Song+Yang%2C+Wenzheng+Xu%2C+Zichuan+Xu%2C+Yao+Wan%2C+Lichao+Sun%2C+and+Zeyu+Xiong%2E+2022%2E+Rethinking+the+video+sampling+and+reasoning+strategies+for+temporal)
77. Haolin Yang, Feilong Tang, Linxiao Zhao, Xiang An, Ming Hu, Huifa Li, Xinlin Zhuang, Boqian Wang, Yifan Lu, Xiaofeng Zhang, and 1 others. 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+Linxiao+Zhao%2C+Xiang+An%2C+Ming+Hu%2C+Huifa+Li%2C+Xinlin+Zhuang%2C+Boqian+Wang%2C+Yifan+Lu%2C+Xiaofeng+Zhang%2C+and+1+others%2E+2025b%2E+Streamagent%3A+Towards+anticipatory+agents+for+streaming+)
78. Jihan Yang, Shusheng Yang, Anjali W Gupta, Rilyn Han, Li Fei-Fei, and Saining Xie. 2025c. [Thinking in space: How multimodal large language models see, remember, and recall spaces](https://md.research.elamur.ai/free/en/papers/yang-2024-thinking-space-multimodal-large-language/). In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 10632–10643.
79. Fangxu Yu, Lai Jiang, Haoqiang Kang, Shibo Hao, and Lianhui Qin. 2024. Flow of reasoning: Training llms for divergent problem solving with minimal examples. arXiv preprint arXiv:2406.05673. — [arXiv:2406.05673](https://arxiv.org/abs/2406.05673) [find](https://scholar.google.com/scholar?q=Fangxu+Yu%2C+Lai+Jiang%2C+Haoqiang+Kang%2C+Shibo+Hao%2C+and+Lianhui+Qin%2E+2024%2E+Flow+of+reasoning%3A+Training+llms+for+divergent+problem+solving+with+minimal+examples%2E+arXiv+preprint+arXiv%3A2406%2E05673%2E+%E2%80%94+%5BarXiv%3A2)
80. Fangxu Yu, Hongyu Zhao, and Tianyi Zhou. 2025. Ts-reasoner: Aligning time series foundation models with llm reasoning. arXiv preprint arXiv:2510.03519. — [arXiv:2510.03519](https://arxiv.org/abs/2510.03519) [find](https://scholar.google.com/scholar?q=Fangxu+Yu%2C+Hongyu+Zhao%2C+and+Tianyi+Zhou%2E+2025%2E+Ts%2Dreasoner%3A+Aligning+time+series+foundation+models+with+llm+reasoning%2E+arXiv+preprint+arXiv%3A2510%2E03519%2E+%E2%80%94+%5BarXiv%3A2510%2E03519%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2510%2E)
81. Xiangyu Zeng, Kunchang Li, Chenting Wang, Xinhao Li, Tianxiang Jiang, Ziang Yan, Songze Li, Yansong Shi, Zhengrong Yue, Yi Wang, Yali Wang, Yu Qiao, and Limin Wang. 2025. Timesuite: Improving MLLMs for long video understanding via grounded tuning. In The Thirteenth International Conference on Learni… [find](https://scholar.google.com/scholar?q=Xiangyu+Zeng%2C+Kunchang+Li%2C+Chenting+Wang%2C+Xinhao+Li%2C+Tianxiang+Jiang%2C+Ziang+Yan%2C+Songze+Li%2C+Yansong+Shi%2C+Zhengrong+Yue%2C+Yi+Wang%2C+Yali+Wang%2C+Yu+Qiao%2C+and+Limin+Wang%2E+2025%2E+Timesuite%3A+Improving+MLLMs+fo)
82. Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, and Limin Wang. 2025. Timelens: Rethinking video temporal grounding with multimodal llms. arXiv preprint arXiv:2512.14698. — [arXiv:2512.14698](https://arxiv.org/abs/2512.14698) [find](https://scholar.google.com/scholar?q=Jun+Zhang%2C+Teng+Wang%2C+Yuying+Ge%2C+Yixiao+Ge%2C+Xinhao+Li%2C+Ying+Shan%2C+and+Limin+Wang%2E+2025%2E+Timelens%3A+Rethinking+video+temporal+grounding+with+multimodal+llms%2E+arXiv+preprint+arXiv%3A2512%2E14698%2E+%E2%80%94+%5BarXiv%3A25)
83. Songyang Zhang, Houwen Peng, Jianlong Fu, and Jiebo Luo. 2020. Learning 2d temporal adjacent networks for moment localization with natural language. In Proceedings of the AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Songyang+Zhang%2C+Houwen+Peng%2C+Jianlong+Fu%2C+and+Jiebo+Luo%2E+2020%2E+Learning+2d+temporal+adjacent+networks+for+moment+localization+with+natural+language%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial)
84. Method Time-R1-3B Qwen-2.5-VL-3B A RROW GEV-3B R1@0.3 R1@0.5 R1@0.7 mIOU R1@0.3 R1@0.5 R1@0.7 mIOU R1@0.3 R1@0.5 R1@0.7 mIOU 62.6 42.9 64.9 40.0 26.9 42.5 18.2 12.8 19.7 40.7 28.7 42.3 34.8 22.0 36.1 19.8 11.5 19.4 9.0 4.8 9.9 23.7 15.7 24.3 30.5 18.0 31.0 17.0 9.8 18.6 8.0 5.2 7.5 19.8 12.6 20.3 *T… [find](https://scholar.google.com/scholar?q=Method+Time%2DR1%2D3B+Qwen%2D2%2E5%2DVL%2D3B+A+RROW+GEV%2D3B+R1%400%2E3+R1%400%2E5+R1%400%2E7+mIOU+R1%400%2E3+R1%400%2E5+R1%400%2E7+mIOU+R1%400%2E3+R1%400%2E5+R1%400%2E7+mIOU+62%2E6+42%2E9+64%2E9+40%2E0+26%2E9+42%2E5+18%2E2+12%2E8+19%2E7+40%2E7+28%2E7+42%2E3+34%2E8+22%2E0+36%2E1+)

*Updated 2 November 2026*