Skip to content

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

active 2025-03-262025-09-24 (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
251
Pushes
5
Pull requests
0
Issues
40
Stars
136
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 183 days from 2025-03-26 to 2025-09-24. Pushes: 5 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 40 total, peak 7 in a day. Comments: 63 total, peak 8 in a day. Stars: 136 total, peak 5 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

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#83yuchenlichuck2025-09-22 20:55
    About Open-Sourcing Qwen Training Code
  • Issue comment#92MSiam2025-09-22 12:46
    Baseline Results for Sa2VA - No Training Involved
  • Issue comment#94HarborYuan2025-09-22 07:54
    Question about Ref-SAV
  • Issue#94wuzy21152025-09-22 07:48
    Question about Ref-SAV
  • Issue comment#93bitersun2025-09-20 12:11
    How to run the sa2va in multi nodes
  • Issue#66bitersun2025-09-20 12:04
    Full evaluation results on ReVOS
  • Issue comment#66bitersun2025-09-20 12:03
    Full evaluation results on ReVOS
  • Issue comment#93yuchenlichuck2025-09-19 22:13
    How to run the sa2va in multi nodes
  • Issue#92MSiam2025-09-19 06:29
    Baseline Results for Sa2VA - No Training Involved
  • Issue comment#84MSiam2025-09-19 06:27
    Sa2VA Baseline Results Inquiry
  • Issue comment#46eslambakr2025-09-18 21:03
    how could i use my dataset to train Sa2VA
  • Issue comment#41HarborYuan2025-09-17 22:19
    [SEG] token usage clarification
  • Issue comment#72yuchenlichuck2025-09-16 22:43
    Can it support multi-card inference?
  • Issue comment#72yuchenlichuck2025-09-16 22:43
    Can it support multi-card inference?
  • Issue#63lxtGH2025-09-15 03:46
    Release Ref-SAM-v and PerBench datasets on Hugging Face
  • Issue comment#63lxtGH2025-09-15 03:46
    Release Ref-SAM-v and PerBench datasets on Hugging Face
  • Issue comment#91HarborYuan2025-09-14 23:52
    Does your code can be trained on multiple nodes
  • Issue#59Luffy032025-09-14 08:27
    Finetune SA2VA on our own datasets
  • Issue comment#59lxtGH2025-09-14 06:05
    Finetune SA2VA on our own datasets
  • Issue comment#35lxtGH2025-09-14 02:39
    How do I load a pre-trained model for fine-tuning?
  • Issue#35lxtGH2025-09-14 02:39
    How do I load a pre-trained model for fine-tuning?
  • Issue#90lxtGH2025-09-12 07:36
    shape mismatch
  • Issue#89lxtGH2025-09-11 05:11
    如何同时使用视觉提示和文本提示来分割视频
  • Issue comment#67XhqGlorry112025-09-10 03:06
    Hidden States of SEG token
  • Issue#70lxtGH2025-09-10 02:38
    Inconsistent performance

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 136 stars here means stars gained during the window, not the repo's star count.