Skip to content

EvolvingLMMs-Lab/OneVision-Encoder

View on GitHub ↗Related repositories →

The first HEVC style Vision Transformer with advanced multimodal capabilities

active 2025-12-252026-06-20 (UTC)

Partial coverage13,872 / 16,569 hourly files (84%) · 2 absent upstream · 2,696 failed, retryable2024-09-202026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
506
Pushes
124
Pull requests
85
Issues
9
Stars
110
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 178 days from 2025-12-25 to 2026-06-20. Pushes: 124 total, peak 16 in a day. Pull requests: 85 total, peak 9 in a day. Issues: 9 total, peak 2 in a day. Comments: 84 total, peak 20 in a day. Stars: 110 total, peak 13 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
Copilot208495867
anxiangsir72401910
FeilongTangmonash252013
Luodian13651
YunyaoYan5311
yiyexy4400
hanzifan3001
Ray-ui1000
bsflll1010
jiankangdeng1100
lucasjinreal1001
RRooyyCChheenn1000
Feilong6071100

Recent activity

Latest issues, pull requests and releases

  • Pull request#119bsflll2026-05-05 19:03
  • Pull request#114YunyaoYan2026-04-15 11:20
  • Pull request#111anxiangsir2026-04-09 05:50
  • Pull request#110anxiangsir2026-04-09 04:26
  • Issue#108anxiangsir2026-04-09 03:28
    📖 Interactive Explainers for Common Questions (GitHub Pages)
  • Issue#105anxiangsir2026-04-09 03:04
    Clarification on how OCR annotations are used during training
  • Issue#100FeilongTangmonash2026-03-12 06:01
    error in patch budget ablation table values
  • Issue comment#103hanzifan2026-03-11 12:13
    How can I install the cv_reader
  • Issue comment#103YunyaoYan2026-02-28 09:12
    How can I install the cv_reader
  • Issue#102hanzifan2026-02-28 02:50
    How can I use Megatron framework to train the OneVision-Encoder+Qwen3?
  • Issue comment#102anxiangsir2026-02-28 02:34
    How can I use Megatron framework to train the OneVision-Encoder+Qwen3?
  • Issue#101RRooyyCChheenn2026-02-27 05:57
    Question regarding missing file dataloader/data_decord_video.py
  • Issue comment#100FeilongTangmonash2026-02-26 02:02
    error in patch budget ablation table values
  • Issue#96Luodian2026-02-18 07:03
    How to construct my own training data
  • Issue comment#96Luodian2026-02-18 04:03
    How to construct my own training data
  • Issue comment#97lucasjinreal2026-02-14 01:36
    Test vision encoder only frames 32 out of memory on 16GB GPU
  • Issue#96hanzifan2026-02-12 02:50
    How to construct my own training data
  • Pull request#95Copilot2026-02-11 02:36
  • Pull request#95Copilot2026-02-11 02:36
  • Pull request#95Copilot2026-02-11 02:36
  • Pull request#82Luodian2026-02-10 05:21
  • Pull request#92Copilot2026-02-10 03:44
  • Pull request#91Copilot2026-02-09 08:02
  • Pull request#90Copilot2026-02-07 15:18
  • Pull request#87Copilot2026-02-07 14:47

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 110 stars here means stars gained during the window, not the repo's star count.