VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
active 2024-12-31 → 2025-07-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 196 days from 2024-12-31 to 2025-07-24. Pushes: 5 total, peak 2 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 12 total, peak 2 in a day. Comments: 18 total, peak 4 in a day. Stars: 157 total, peak 10 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 |
|---|---|---|---|---|
| Uranusxer | 10 | 2 | 0 | 7 |
| xujz18 | 4 | 3 | 0 | 1 |
| anvilarth | 3 | 0 | 1 | 2 |
| X-fxx | 2 | 0 | 0 | 0 |
| YujieOuO | 2 | 0 | 0 | 0 |
| weTerence | 2 | 0 | 0 | 2 |
| gsfsdv | 1 | 0 | 0 | 1 |
| KT313 | 1 | 0 | 0 | 1 |
| wsxwd | 1 | 0 | 0 | 1 |
| liangbingzhao | 1 | 0 | 0 | 1 |
| jinzhuoran | 1 | 0 | 0 | 1 |
| yuanygong | 1 | 0 | 0 | 1 |
| ucaswindlike | 1 | 0 | 0 | 0 |
| LISTEN7SYW | 1 | 0 | 0 | 0 |
| GongXinyuu | 1 | 0 | 0 | 0 |
| shredder67 | 1 | 0 | 0 | 0 |
| haoxian-chen | 1 | 0 | 0 | 0 |
| shencuifeng | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#19LISTEN7SYW2025-05-03 07:27MPO's codes
- Issue#14shredder672025-04-18 13:45scores with full qa version
- Issue#11YujieOuO2025-04-06 08:22No module named 'ImageReward'
- Issue comment#12Uranusxer2025-04-06 08:17Weight数目与question不匹配
- Issue comment#13Uranusxer2025-04-06 08:06cuda out of memory
- Issue#9Uranusxer2025-04-06 08:02tar model
- Issue comment#11Uranusxer2025-04-06 08:02No module named 'ImageReward'
- Issue comment#14Uranusxer2025-04-06 07:57scores with full qa version
- Issue#12X-fxx2025-03-29 07:04Weight数目与question不匹配
- Issue#11YujieOuO2025-03-28 05:21No module named 'ImageReward'
- Issue comment#9weTerence2025-03-13 02:09tar model
- Issue comment#9weTerence2025-03-12 02:34tar model
- Issue#9X-fxx2025-03-02 08:56tar model
- Issue comment#4liangbingzhao2025-02-16 12:17推理速度
- Issue comment#6Uranusxer2025-02-16 07:53期待数据可以开源
- Issue comment#4Uranusxer2025-02-16 07:30推理速度
- Issue#8haoxian-chen2025-02-16 05:38CUDA OOM and Data Type Mismatch in Inference with L40S GPUs
- Issue comment#6jinzhuoran2025-02-14 06:51期待数据可以开源
- Issue comment#2xujz182025-02-13 02:21Release VisionReward dataset on Hugging Face
- Issue comment#4yuanygong2025-02-07 06:19推理速度
- Issue#7GongXinyuu2025-02-01 06:39Index put requires the source and destination dtypes match, got BFloat16 for the destination and Float for the source.
- Issue#6ucaswindlike2025-01-24 03:08期待数据可以开源
- Issue comment#4gsfsdv2025-01-21 07:32推理速度
- Issue comment#1anvilarth2025-01-19 17:42Hi, when will you release the THUDM/VisionReward-Image weight?
- Issue comment#5anvilarth2025-01-19 17:38fix of import error
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 157 stars here means stars gained during the window, not the repo's star count.