Skip to content

Reproduce of Pixel-Level Reasoning Model trained with RL [NeuIPS25]

active 2025-05-182026-05-01 (UTC)

Complete coverage26,781 / 26,781 hourly files (100%) · 2 absent upstream2023-08-152026-09-03 (UTC)
Events
321
Pushes
59
Pull requests
0
Issues
40
Stars
159
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 349 days from 2025-05-18 to 2026-05-01. Pushes: 59 total, peak 12 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 40 total, peak 4 in a day. Comments: 52 total, peak 5 in a day. Stars: 159 total, peak 12 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

Recent activity

Latest issues, pull requests and releases

  • Issue comment#39cjakfskvnad2026-01-04 01:51
    Pixel Reasoner Tool Call Frequency Gradually Approaches Zero in Verl-tool
  • Issue comment#34cjakfskvnad2026-01-04 01:45
    KeyError: 'type' in PixelReasoner-SFT-Data
  • Issue#37cjakfskvnad2026-01-04 01:24
    How was the Qwen2.5-VL 7B configuration and system prompt settings defined in Table 1 in paper?
  • Issue comment#38cjakfskvnad2026-01-04 01:09
    CPU memory usage for PixelReasoner
  • Issue#33wenhuchen2026-01-03 20:16
    Why verl-tool's pixel reasoner (82.7) lead to much lower performance than pixel reasoner in this repo (84.3)?
  • Issue#38zulihit2025-12-04 11:55
    CPU memory usage for PixelReasoner
  • Issue#354NLLab2025-11-11 03:09
    ImportError: cannot import name 'Qwen2_5_VLVisionFlashAttention2' from transformers.models.qwen2_5_vl
  • Issue comment#35cjakfskvnad2025-11-06 06:30
    ImportError: cannot import name 'Qwen2_5_VLVisionFlashAttention2' from transformers.models.qwen2_5_vl
  • Issue comment#32HaozheH32025-10-03 05:25
    Unable to reproduce PixelReasoner Cold-Start performance on vstar
  • Issue#28HaozheH32025-07-25 13:39
    Difficulty in Reproducing Results
  • Issue comment#31EugeneLiu012025-07-22 04:21
    Actor/policy loss steep rise, and mean reward steep fall
  • Issue#31EugeneLiu012025-07-22 03:49
    Actor/policy loss steep rise, and mean reward steep fall
  • Issue#30wuzhaodongaipython2025-07-18 06:41
    How long to train the model with 8*A800(80G)
  • Issue comment#27mf-zhang2025-07-07 07:55
    Could you share your pip list for RL setup?
  • Issue comment#27HaozheH32025-07-07 04:31
    Could you share your pip list for RL setup?
  • Issue comment#27HaozheH32025-07-06 13:42
    Could you share your pip list for RL setup?
  • Issue#27mf-zhang2025-07-06 12:55
    Could you share your pip list for RL setup?
  • Issue comment#26HaozheH32025-07-02 13:03
    stuck in the single-node rl training
  • Issue#26HaozheH32025-07-02 13:03
    stuck in the single-node rl training
  • Issue comment#26g-makerr2025-07-02 12:59
    stuck in the single-node rl training
  • Issue comment#26HaozheH32025-07-02 12:17
    stuck in the single-node rl training
  • Issue comment#26g-makerr2025-07-02 07:12
    request for environment.yaml
  • Issue#26g-makerr2025-07-02 07:11
    request for environment.yaml
  • Issue#13HaozheH32025-06-30 11:58
    Simple inference demo
  • Issue#23HaozheH32025-06-30 11:57
    the meaning of normalized coordinates in bbox

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 159 stars here means stars gained during the window, not the repo's star count.