[NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
active 2025-05-27 → 2026-04-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 310 days from 2025-05-27 to 2026-04-01. Pushes: 4 total, peak 2 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 6 total, peak 2 in a day. Comments: 7 total, peak 3 in a day. Stars: 58 total, peak 21 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 |
|---|---|---|---|---|
| Jxzh2020 | 4 | 3 | 0 | 1 |
| AlexiaJM | 3 | 0 | 0 | 2 |
| Z-MU-Z | 3 | 0 | 1 | 1 |
| erjanmx | 1 | 0 | 1 | 0 |
| WJJArvin | 1 | 0 | 0 | 0 |
| gak97 | 1 | 0 | 0 | 0 |
| CJack812 | 1 | 0 | 0 | 0 |
| haoz0206 | 1 | 1 | 0 | 0 |
| JoshonSmith | 1 | 0 | 0 | 0 |
| PussyCat0700 | 1 | 0 | 0 | 1 |
| peterwisu | 1 | 0 | 0 | 1 |
| TOM-ZHOUch | 1 | 0 | 0 | 1 |
| HPUhushicheng | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#7peterwisu2026-04-01 15:08Training compute / resources used for Omni-R1 (GPU type/count, time, steps)
- Issue comment#8Z-MU-Z2025-12-16 07:27Qwen2.5-Omni微调的是thinker部分还是talker部分？
- Issue#8JoshonSmith2025-12-16 02:54Qwen2.5-Omni微调的是thinker部分还是talker部分？
- Issue#7WJJArvin2025-12-13 02:18Training compute / resources used for Omni-R1 (GPU type/count, time, steps)
- Issue comment#6PussyCat07002025-12-02 03:33What are the connections and differences between Omni-R1 and R1-Omni?
- Issue comment#2TOM-ZHOUch2025-09-25 14:10Release the segmentation and evaluation code, training scripts
- Issue#6HPUhushicheng2025-09-02 15:42What are the connections and differences between Omni-R1 and R1-Omni?
- Issue#5CJack8122025-09-02 05:40why there is no think tag in the output
- Issue#4gak972025-06-28 21:12Dataset preparation info does not exist
- Issue comment#3Jxzh20202025-06-10 19:43is it possible to serve the model using a server (vllm, sglang, etc.)
- Issue comment#3AlexiaJM2025-06-10 15:12is it possible to serve the model using a server (vllm, sglang, etc.)
- Issue comment#3AlexiaJM2025-06-10 14:36is it possible to serve the model using a server (vllm, sglang, etc.)
- Issue#3AlexiaJM2025-06-10 12:57is it possible to serve the model using a server (vllm, sglang, etc.)
- Pull request#1Z-MU-Z2025-06-03 06:28
- Pull request#1erjanmx2025-06-01 18:00
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 58 stars here means stars gained during the window, not the repo's star count.