Skip to content

dvlab-research/VisionReasoner

View on GitHub ↗Related repositories →

Vision Manus: Your versatile Visual AI assistant

active 2025-05-182025-12-30 (UTC)

Partial coverage11,294 / 12,108 hourly files (93%) · 2 absent upstream · 812 failed, retryable2025-03-242026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
233
Pushes
10
Pull requests
0
Issues
26
Stars
150
Forks
10

Activity over time

Daily event counts in the loaded window

Line chart, 227 days from 2025-05-18 to 2025-12-30. Pushes: 10 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 26 total, peak 2 in a day. Comments: 37 total, peak 5 in a day. Stars: 150 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
LiuRicky427023
connorye3001
xin-ran-w3002
tzjtatata3002
twangnh2001
DWL3212002
WeitaiKang2001
xinyann6662001
taintaintainu2200
lizi19971000
zhuhrun1000
JumpXing1001
yyliu011000
LFL199910031000
Huster-Hq1000
yuchenlichuck1001
zhutianlee1001
qiwang0671000
paynezhangpayne1001

Recent activity

Latest issues, pull requests and releases

  • Issue#27xinyann6662025-12-26 02:24
    Question on the LISA++ subset used in VisionReasoner_multi_object_7k_840
  • Issue comment#27xinyann6662025-12-26 02:24
    Question on the LISA++ subset used in VisionReasoner_multi_object_7k_840
  • Issue comment#27LiuRicky2025-12-25 11:23
    Question on the LISA++ subset used in VisionReasoner_multi_object_7k_840
  • Issue comment#26LiuRicky2025-10-28 02:09
    The OOD meaning
  • Issue#24yyliu012025-09-13 19:15
    Inconsistent result (possible typo) between Table 9 in Seg-Zero paper and Table 3 in VisionReasoner paper
  • Issue#22LiuRicky2025-09-08 02:39
    分割解码策略
  • Issue#23LiuRicky2025-09-06 10:46
    About the metrics
  • Issue#23zhuhrun2025-09-04 02:18
    About the metrics
  • Issue#22Huster-Hq2025-08-28 12:29
    分割解码策略
  • Issue comment#19yuchenlichuck2025-08-25 21:16
    GRPO training lower the peformance of SFT training in medical domain
  • Issue comment#21LiuRicky2025-08-17 08:13
    Ask for the full data generation pipeline
  • Issue comment#21WeitaiKang2025-08-16 13:18
    Ask for the full data generation pipeline
  • Issue comment#21LiuRicky2025-08-16 06:13
    Ask for the full data generation pipeline
  • Issue#21WeitaiKang2025-08-15 17:47
    Ask for the full data generation pipeline
  • Issue#20LiuRicky2025-08-15 15:57
    Question about AP calculation in MLLM-based object detection without explicit scores
  • Issue comment#20LiuRicky2025-08-13 12:26
    Question about AP calculation in MLLM-based object detection without explicit scores
  • Issue#19connorye2025-07-20 14:53
    GRPO training lower the peformance of SFT training in medical domain
  • Issue#18LiuRicky2025-07-18 02:20
    can you share the training datas?
  • Issue#17LiuRicky2025-07-09 08:05
    Why are the values ​​in the performance comparison table are different from those in the Qwen2.5-VL report
  • Issue comment#17LiuRicky2025-07-09 08:05
    Why are the values ​​in the performance comparison table are different from those in the Qwen2.5-VL report
  • Issue comment#17JumpXing2025-07-09 07:08
    Why are the values ​​in the performance comparison table are different from those in the Qwen2.5-VL report
  • Issue comment#17LiuRicky2025-07-09 06:36
    Why are the values ​​in the performance comparison table are different from those in the Qwen2.5-VL report
  • Issue comment#17LiuRicky2025-07-09 06:29
    Why are the values ​​in the performance comparison table are different from those in the Qwen2.5-VL report
  • Issue comment#16twangnh2025-07-09 02:16
    the 500 vision tasks
  • Issue#16twangnh2025-07-07 11:17
    the 500 vision tasks

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 150 stars here means stars gained during the window, not the repo's star count.