[CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
active 2025-11-26 → 2026-06-24 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 211 days from 2025-11-26 to 2026-06-24. Pushes: 48 total, peak 9 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 20 total, peak 7 in a day. Comments: 14 total, peak 3 in a day. Stars: 89 total, peak 29 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| mwxely | 59 | 38 | 0 | 8 |
| XIAO4579 | 7 | 7 | 0 | 0 |
| KemingWu | 3 | 3 | 0 | 0 |
| wkfdb | 3 | 0 | 0 | 2 |
| alanshaoTT | 2 | 0 | 0 | 1 |
| whu125 | 1 | 0 | 0 | 0 |
| Yusux | 1 | 0 | 0 | 0 |
| kcz358 | 1 | 0 | 0 | 1 |
| fazhdo | 1 | 0 | 0 | 0 |
| smileformylove | 1 | 0 | 0 | 1 |
| HiFiChang | 1 | 0 | 0 | 1 |
| loganionian | 1 | 0 | 1 | 0 |
| Yuanhong-Zheng | 1 | 0 | 0 | 0 |
| Xnhyacinth | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#22Xnhyacinth2026-05-23 16:05VideoMMMU tool YAML where generation_kwargs is concatenated with process_results
- Issue comment#16smileformylove2026-05-20 01:47请问在RL阶段，训练时模型每次的rollout都是实际调用了工具并且把结果返回给下一轮的推理吗？还是只模拟tool response，没有实际获取工具调用的实际结果呢？
- Issue comment#19kcz3582026-03-22 08:07Questions about the evaluation.
- Issue comment#18mwxely2026-03-12 10:47Question about Gemini-Distilled iMCoTT Data
- Issue comment#15HiFiChang2026-02-15 13:52LongVT-RL在videomme上tool_call频率非常低
- Pull request#17loganionian2026-02-12 13:02
- Issue comment#16alanshaoTT2026-02-10 05:51请问在RL阶段，训练时模型每次的rollout都是实际调用了工具并且把结果返回给下一轮的推理吗？还是只模拟tool response，没有实际获取工具调用的实际结果呢？
- Issue#13mwxely2026-02-10 05:02Script run_imcott_generate.shmentioned in README is missing from the scripts/directory
- Issue#8mwxely2026-02-10 04:59Excellent work! Are there any version requirements for the lmms-engine library? Thank you.
- Issue#9mwxely2026-02-10 04:59problem in starting 72b server for train and eval
- Issue#12mwxely2026-02-10 04:58Problem on single_inference.py
- Issue#8mwxely2026-02-10 04:57Excellent work! Are there any version requirements for the lmms-engine library? Thank you.
- Issue#6mwxely2026-02-10 04:55Request for a demo code example
- Issue#16mwxely2026-02-10 04:49请问在RL阶段，训练时模型每次的rollout都是实际调用了工具并且把结果返回给下一轮的推理吗？还是只模拟tool response，没有实际获取工具调用的实际结果呢？
- Issue#16alanshaoTT2026-02-08 13:51请问在RL阶段，训练时模型每次的rollout都是实际调用了工具并且把结果返回给下一轮的推理吗？还是只模拟tool response，没有实际获取工具调用的实际结果呢？
- Issue comment#13mwxely2026-01-31 15:16Script run_imcott_generate.shmentioned in README is missing from the scripts/directory
- Issue comment#13mwxely2026-01-25 02:41Script run_imcott_generate.shmentioned in README is missing from the scripts/directory
- Issue#8mwxely2026-01-08 19:57Excellent work! Are there any version requirements for the lmms-engine library? Thank you.
- Issue comment#8mwxely2026-01-08 19:57Excellent work! Are there any version requirements for the lmms-engine library? Thank you.
- Issue comment#11mwxely2026-01-08 19:53Question about metrics when evaluating LVBench
- Issue#12fazhdo2026-01-06 05:43Problem on single_inference.py
- Issue comment#10wkfdb2025-12-30 09:07Json Error in evaluation process
- Issue comment#11mwxely2025-12-30 08:54Question about metrics when evaluating LVBench
- Issue#6mwxely2025-12-30 08:29Request for a demo code example
- Issue#7mwxely2025-12-30 08:29How to get video_summaries.json
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 89 stars here means stars gained during the window, not the repo's star count.