Video-R1: Towards Super Reasoning Ability in Video Understanding MLLMs
active 2025-02-23 → 2026-06-04 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 467 days from 2025-02-23 to 2026-06-04. Pushes: 33 total, peak 6 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 82 total, peak 3 in a day. Comments: 164 total, peak 18 in a day. Stars: 370 total, peak 27 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 |
|---|---|---|---|---|
| tulerfeng | 126 | 33 | 1 | 89 |
| Fu-Fu-Fu-Fu | 14 | 0 | 0 | 9 |
| HarryHsing | 7 | 0 | 1 | 5 |
| 2402227288 | 7 | 0 | 0 | 2 |
| GX77 | 6 | 0 | 0 | 4 |
| yuchuanhui | 6 | 0 | 0 | 2 |
| 1171-jpg | 5 | 0 | 0 | 3 |
| hupf3 | 4 | 0 | 0 | 2 |
| WPR001 | 4 | 0 | 0 | 3 |
| fushh | 4 | 0 | 0 | 1 |
| Lexarymade | 3 | 0 | 0 | 1 |
| Yuejingkun | 3 | 0 | 0 | 3 |
| zl3466 | 3 | 0 | 0 | 2 |
| TUDelftHao | 3 | 0 | 0 | 1 |
| hlchen23 | 3 | 0 | 0 | 1 |
| Hongbo-Jin | 3 | 0 | 0 | 2 |
| richhh520 | 3 | 0 | 0 | 1 |
| markinruc | 3 | 0 | 0 | 1 |
| Quibbler6 | 3 | 0 | 0 | 2 |
| Parsifal133 | 3 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#127tulerfeng2026-04-07 10:28Request for Video-R1 3B model training data and weights
- Issue comment#126yukui922026-03-01 01:37请问使用eval_bench.py来测试不同的benchmark大概需要多久呢？
- Issue#126yukui922026-02-28 14:25请问使用eval_bench.py来测试不同的benchmark大概需要多久呢？
- Issue comment#125tulerfeng2026-02-09 04:47Training crash with "uncorrectable ECC error" and NCCL timeout?
- Issue comment#124tulerfeng2026-02-01 17:59OUT OF MEMory on 4 a100 gpus
- Issue comment#124MohdUbaidwani2026-02-01 17:46OUT OF MEMory on 4 a100 gpus
- Issue#123Fu-Fu-Fu-Fu2026-01-24 05:17请问basemodel：qwen2.5vl的结果是用什么prompt测试的？
- Issue comment#122tulerfeng2026-01-22 20:00如何评估SFT训练性能
- Issue#12224022272882026-01-20 06:23如何评估SFT训练性能
- Issue comment#12024022272882026-01-15 09:13SFT数据集生成
- Issue comment#120tulerfeng2026-01-14 15:25SFT数据集生成
- Issue comment#120tulerfeng2026-01-14 09:39SFT数据集生成
- Issue#12024022272882026-01-14 02:33SFT数据集生成
- Issue#11924022272882026-01-12 03:22dataloader_num_workers
- Issue comment#34ustiniansy2026-01-10 15:08RuntimeError: split_with_sizes expects split_sizes to sum exactly to 1 (input tensor's size at dimension 0), but got split_sizes=[0]
- Issue#11924022272882026-01-09 10:25dataloader_num_workers
- Issue comment#118tulerfeng2026-01-07 08:29可以提供Video-R1-7B-wo-image的模型吗
- Issue comment#11524022272882025-12-30 07:45GRPO训练曲线问题
- Issue comment#115tulerfeng2025-12-30 07:19GRPO训练曲线问题
- Issue#11424022272882025-12-23 11:18training waring
- Issue comment#113wwxs123W2025-12-22 08:47How to change the frame when training？
- Issue comment#112tulerfeng2025-12-20 14:07GRPO Trainer训练过程中NCCL通信问题
- Issue comment#111tulerfeng2025-12-18 16:08grpo脚本中的max_pixels是什么？
- Issue comment#39tulerfeng2025-12-07 14:38IndexError: index 1 is out of bounds for dimension 0 with size 1
- Issue comment#3910-OASIS-012025-12-07 14:30IndexError: index 1 is out of bounds for dimension 0 with size 1
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 370 stars here means stars gained during the window, not the repo's star count.