Skip to content

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing [ICLR 2026]

active 2025-10-012026-06-07 (UTC)

Complete coverage26,504 / 26,504 hourly files (100%) · 2 absent upstream2023-08-152026-08-23 (UTC)
Events
108
Pushes
23
Pull requests
3
Issues
18
Stars
54
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 250 days from 2025-10-01 to 2026-06-07. Pushes: 23 total, peak 4 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 18 total, peak 2 in a day. Comments: 7 total, peak 2 in a day. Stars: 54 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
KemingWu302034
JohnsonJiang19966303
BUAAPY2000
g-h-chen2000
KZF-kzf2000
wzh3262000
scuhappy1000
duyc1681000
tls05231000
PlutoQyl1000
TyangJN1000
akk-1231000
YourYongKing1000

Recent activity

Latest issues, pull requests and releases

  • Issue#29PlutoQyl2026-06-07 01:58
    aggregation_threshold
  • Issue#19KemingWu2026-04-12 06:29
    Scores are always negative when using EditRewardInferencer with reward_dim="overall_detail"
  • Pull request#27KemingWu2026-04-11 05:23
  • Issue#24KZF-kzf2026-02-24 03:57
    Does the reward_dim parameter actually do anything?
  • Issue comment#23KemingWu2026-02-04 03:41
    Fix wrong arxiv link in README.md
  • Issue#20BUAAPY2026-01-29 07:36
    train.json
  • Pull request#22KemingWu2026-01-27 06:13
  • Pull request#22KemingWu2026-01-27 06:13
  • Issue#21KZF-kzf2026-01-27 03:29
    Questions for mode == "single_inference"
  • Issue#20BUAAPY2026-01-20 06:38
    train.json
  • Issue#19tls05232025-12-24 03:41
    Scores are always negative when using EditRewardInferencer with reward_dim="overall_detail"
  • Issue comment#17JohnsonJiang19962025-12-22 22:59
    Does EditReward support Chinese for edit instructions?
  • Issue#18wzh3262025-12-22 02:59
    How to evaluate reward models on ImageHub?
  • Issue#18wzh3262025-12-22 02:49
    How to evaluate reward models on ImageHub?
  • Issue#16scuhappy2025-12-17 05:02
    I'd like to know how long the author trained.
  • Issue comment#15JohnsonJiang19962025-12-10 20:37
    Conflicting annotations in 2pair and mismatch with reported MIMO per-K metrics
  • Issue#13KemingWu2025-12-02 06:37
    💦
  • Issue comment#13KemingWu2025-11-29 06:00
    💦
  • Issue comment#14KemingWu2025-11-29 06:00
    dataset issue-duplicated samples in benchmark with different preference labels
  • Issue#14g-h-chen2025-11-28 03:22
    dataset issue-duplicated samples in benchmark with different preference labels
  • Issue#13YourYongKing2025-11-21 10:57
    💦
  • Issue#6KemingWu2025-10-24 12:07
    RL training code
  • Issue comment#9KemingWu2025-10-23 20:51
    multi-source editing evaluation
  • Issue#9TyangJN2025-10-23 14:12
    multi-source editing evaluation
  • Issue#7duyc1682025-10-21 08:52
    code to evaluate proposed EditReward reward model on proposed EditReward Bench

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 54 stars here means stars gained during the window, not the repo's star count.