Skip to content

Verifiers for VLM Reinforcement Learning

active 2025-02-112025-09-20 (UTC)

Partial coverage13,898 / 16,623 hourly files (84%) · 2 absent upstream · 2,725 failed, retryable2024-09-172026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
3.2K
Pushes
562
Pull requests
205
Issues
167
Stars
1.6K
Forks
192

Activity over time

Daily event counts in the loaded window

Line chart, 222 days from 2025-02-11 to 2025-09-20. Pushes: 562 total, peak 45 in a day. Pull requests: 205 total, peak 13 in a day. Issues: 167 total, peak 10 in a day. Comments: 383 total, peak 16 in a day. Stars: 1,595 total, peak 166 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
willccbb825436113177
cursor[bot]13211209
CLAassistant600060
mikasenghaas22149
tcapelle16047
srthkdev130130
SamComber12025
skoshx10006
lakshyaag9034
rasdani9013
ljt0199006
Randomdude118005
richardzhuang04127006
oxysoft7003
hrdkbhatnagar6005
sunildkumar6004
Danau5tin5003
cat-state5022
hank03165004
MagellaX5014

Recent activity

Latest issues, pull requests and releases

  • Pull request#350willccbb2025-09-20 05:58
  • Pull request#348willccbb2025-09-20 00:36
  • Pull request#346willccbb2025-09-20 00:25
  • Pull request#347willccbb2025-09-20 00:13
  • Issue comment#332lakshyaag2025-09-19 19:39
    feat: add response format handling in judge rubric
  • Pull request#340Al-aminI2025-09-19 10:18
  • Pull request#345willccbb2025-09-19 06:07
  • Pull request#344willccbb2025-09-19 04:06
  • Issue comment#341willccbb2025-09-18 18:10
    Does the framework support checkpoint saving and resuming training?
  • Issue#341willccbb2025-09-18 18:10
    Does the framework support checkpoint saving and resuming training?
  • Issue#342willccbb2025-09-18 18:08
    test + integrate Weave into trainer
  • Issue#341Zhang-Henry2025-09-18 17:54
    Does the framework support checkpoint saving and resuming training?
  • Issue comment#340CLAassistant2025-09-18 10:09
    Add attn_implementation parameter to get_model_and_tokenizer
  • Pull request#340Al-aminI2025-09-18 10:09
  • Pull request#324willccbb2025-09-18 01:27
  • Pull request#281willccbb2025-09-17 22:13
  • Issue comment#281willccbb2025-09-17 22:12
    feat: update `vf-eval` to use typer and add TUI
  • Issue comment#337willccbb2025-09-17 22:10
    feat(eval): add support for grouped reward summaries and reports
  • Issue comment#317willccbb2025-09-17 22:09
    rename flag to "push_to_hf_hub" for clarity
  • Issue#329willccbb2025-09-17 22:07
    More informative messaging in load_environment for package name collisions
  • Pull request#320willccbb2025-09-17 22:03
  • Pull request#325willccbb2025-09-17 22:03
  • Pull request#326willccbb2025-09-17 22:02
  • Issue comment#338willccbb2025-09-17 22:01
    [DRAFT]: Add Claude Code environment for coding-based tasks
  • Issue comment#332wcummings2025-09-17 16:51
    feat: add response format handling in judge rubric

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,595 stars here means stars gained during the window, not the repo's star count.