Skip to content

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

active 2025-11-262026-05-26 (UTC)

Partial coverage12,272 / 13,978 hourly files (88%) · 2 absent upstream · 1,701 failed, retryable2025-01-052026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
131
Pushes
5
Pull requests
1
Issues
10
Stars
98
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 182 days from 2025-11-26 to 2026-05-26. Pushes: 5 total, peak 2 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 10 total, peak 1 in a day. Comments: 10 total, peak 2 in a day. Stars: 98 total, peak 24 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
gordonhu60811504
wolf9431344973002
wnn20001000
emjay731000
dder4a421001
cf1001
cjfcsjt1000
ZebinX1000
jkhu291001
stjohn20071000
rbler12341010
Elaine61071001
cwchenwang1000
wenzhoulyu1000

Recent activity

Latest issues, pull requests and releases

  • Issue#19emjay732026-05-26 01:57
    [Request] G²VLM-SR checkpoint release
  • Issue#13gordonhu6082026-04-18 22:33
    Question about the eval results
  • Issue comment#16gordonhu6082026-04-18 22:32
    Question About Joint Training Data Pipeline and SFT Dataset Configuration
  • Issue comment#1cf2026-04-18 11:03
    Release G$^2$VLM-SR model and training code on Hugging Face
  • Issue#18wnn20002026-04-15 11:41
    Questions about token ordering and attention masking in the mixed Transformer
  • Issue#16cjfcsjt2026-02-27 15:14
    Question About Joint Training Data Pipeline and SFT Dataset Configuration
  • Pull request#12rbler12342026-01-15 08:07
  • Issue comment#9jkhu292026-01-12 07:58
    Could you provide evaluation code?
  • Issue#8cwchenwang2025-12-30 01:27
    Question on evaluation
  • Issue#7wenzhoulyu2025-12-24 12:15
    Release of training scripts
  • Issue#6ZebinX2025-12-15 09:50
    Poor performance of the other question.
  • Issue comment#3wolf9431344972025-12-10 10:04
    The testing performance is poor
  • Issue comment#3Elaine61072025-12-10 09:53
    The testing performance is poor
  • Issue#5stjohn20072025-12-10 03:51
    Question about inference_chat.py
  • Issue#3gordonhu6082025-12-07 04:41
    The testing performance is poor
  • Issue comment#3gordonhu6082025-12-07 04:41
    The testing performance is poor
  • Issue comment#3dder4a422025-12-05 07:41
    The testing performance is poor
  • Issue#2wolf9431344972025-11-29 08:26
    downstream task
  • Issue comment#2wolf9431344972025-11-29 08:24
    downstream task
  • Issue comment#2gordonhu6082025-11-28 19:50
    downstream task
  • Issue comment#1gordonhu6082025-11-28 19:46
    Release G$^2$VLM-SR model and training code on Hugging Face

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 98 stars here means stars gained during the window, not the repo's star count.