The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]
active 2025-04-11 → 2026-03-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 342 days from 2025-04-11 to 2026-03-18. Pushes: 18 total, peak 8 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 1 in a day. Comments: 6 total, peak 1 in a day. Stars: 81 total, peak 9 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 |
|---|---|---|---|---|
| wenhuchen | 13 | 10 | 0 | 2 |
| HaozheH3 | 9 | 8 | 0 | 1 |
| Kwen-Chen | 2 | 0 | 0 | 1 |
| june6423 | 1 | 0 | 0 | 1 |
| JJumSSu | 1 | 0 | 0 | 0 |
| TimeFlysLeo | 1 | 0 | 0 | 1 |
| Roombreak | 1 | 0 | 0 | 0 |
| MrZilinXiao | 1 | 0 | 0 | 0 |
| MikeWangWZHL | 1 | 0 | 0 | 0 |
| FerryHuang | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#12june64232026-01-19 02:02Version Conflicts — Request for Package Version Information
- Issue#14Roombreak2025-12-18 20:05Data Preprocessing Question
- Issue comment#13HaozheH32025-12-09 19:31TIGER-Lab/ViRL39K数据集从datasets库加载有问题，恳请修正。
- Issue comment#9TimeFlysLeo2025-08-25 06:50Where is version.txt?
- Issue comment#8Kwen-Chen2025-07-17 09:20Inquiry on Evaluation Prompts for Open Source Model
- Issue#8Kwen-Chen2025-07-16 11:13Inquiry on Evaluation Prompts for Open Source Model
- Issue comment#7wenhuchen2025-06-20 22:14论文中7B结果是不是写错了啊
- Issue#6JJumSSu2025-06-16 18:51Question about the dataset subsampling
- Issue#5MikeWangWZHL2025-06-04 04:39What is the held-out validation set being used for choosing the final checkpoint?
- Issue#4FerryHuang2025-05-08 02:24Regarding Reproducing Reported Results
- Issue#2MrZilinXiao2025-05-06 02:33Estimated 32B Model Release Timeline
- Issue#1wenhuchen2025-04-27 23:04Request: Open-source full-size multimodal reasoning model series based on vl-rethinker algorithm
- Issue comment#1wenhuchen2025-04-27 23:04Request: Open-source full-size multimodal reasoning model series based on vl-rethinker algorithm
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 81 stars here means stars gained during the window, not the repo's star count.