Skip to content

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

active 2025-02-182025-12-24 (UTC)

Partial coverage19,073 / 24,549 hourly files (78%) · 2 absent upstream · 5,473 failed, retryable2023-10-242026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
105
Pushes
5
Pull requests
0
Issues
5
Stars
88
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 310 days from 2025-02-18 to 2025-12-24. Pushes: 5 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 5 total, peak 1 in a day. Comments: 6 total, peak 2 in a day. Stars: 88 total, peak 27 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
MiZhenxing8503
avi22bhattacharya2000
kelisiya1001
kforkkk1001
cyf231000
hutaiHang1000
yfChang-cv1000
Orlando-CS1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#7kforkkk2025-11-29 02:46
    Training thinkdiff lvlm config
  • Issue#9avi22bhattacharya2025-11-16 01:55
    Precompute Embeddings Data
  • Issue#8avi22bhattacharya2025-11-02 17:53
    Missing LaionDataset Class
  • Issue comment#7MiZhenxing2025-11-01 03:22
    Training thinkdiff lvlm config
  • Issue comment#5Orlando-CS2025-07-18 08:02
    where is the modelling code?
  • Issue comment#5MiZhenxing2025-07-17 07:55
    where is the modelling code?
  • Issue#4cyf232025-03-18 01:19
    The Role of Explicit Alignment Networks vs. Raw LVLM Capabilities
  • Issue#3hutaiHang2025-03-16 17:54
    How about the results of directly using the text inferred by LVLM as a prompt?
  • Issue#2yfChang-cv2025-02-28 07:36
    When will the code be released?
  • Issue comment#1MiZhenxing2025-02-19 05:35
    Release ThinkDiff checkpoints on Hugging Face
  • Issue comment#1kelisiya2025-02-19 01:52
    Release ThinkDiff checkpoints on Hugging Face

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 88 stars here means stars gained during the window, not the repo's star count.