Skip to content

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

active 2024-12-312025-07-11 (UTC)

Partial coverage20,502 / 26,258 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-13 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
197
Pushes
5
Pull requests
1
Issues
12
Stars
157
Forks
3

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

ContributorContributionsPushesPRsComments
Uranusxer10207
xujz184301
anvilarth3012
X-fxx2000
YujieOuO2000
weTerence2002
gsfsdv1001
KT3131001
wsxwd1001
liangbingzhao1001
jinzhuoran1001
yuanygong1001
ucaswindlike1000
LISTEN7SYW1000
GongXinyuu1000
shredder671000
haoxian-chen1000
shencuifeng1000
NielsRogge1000

Recent activity

Latest issues, pull requests and releases

  • Issue#19LISTEN7SYW2025-05-03 07:27
    MPO's codes
  • Issue#14shredder672025-04-18 13:45
    scores with full qa version
  • Issue#11YujieOuO2025-04-06 08:22
    No module named 'ImageReward'
  • Issue comment#12Uranusxer2025-04-06 08:17
    Weight数目与question不匹配
  • Issue comment#13Uranusxer2025-04-06 08:06
    cuda out of memory
  • Issue#9Uranusxer2025-04-06 08:02
    tar model
  • Issue comment#11Uranusxer2025-04-06 08:02
    No module named 'ImageReward'
  • Issue comment#14Uranusxer2025-04-06 07:57
    scores with full qa version
  • Issue#12X-fxx2025-03-29 07:04
    Weight数目与question不匹配
  • Issue#11YujieOuO2025-03-28 05:21
    No module named 'ImageReward'
  • Issue comment#9weTerence2025-03-13 02:09
    tar model
  • Issue comment#9weTerence2025-03-12 02:34
    tar model
  • Issue#9X-fxx2025-03-02 08:56
    tar 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 05:38
    CUDA 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 02:21
    Release VisionReward dataset on Hugging Face
  • Issue comment#4yuanygong2025-02-07 06:19
    推理速度
  • Issue#7GongXinyuu2025-02-01 06:39
    Index 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 17:42
    Hi, when will you release the THUDM/VisionReward-Image weight?
  • Issue comment#5anvilarth2025-01-19 17:38
    fix 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.