Skip to content

thu-ml/RoboticsDiffusionTransformer

View on GitHub ↗Related repositories →

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

active 2025-02-152026-06-22 (UTC)

Partial coverage11,747 / 13,008 hourly files (90%) · 2 absent upstream · 1,258 failed, retryable2025-02-142026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
450
Pushes
6
Pull requests
5
Issues
29
Stars
341
Forks
29

Activity over time

Daily event counts in the loaded window

Line chart, 493 days from 2025-02-15 to 2026-06-22. Pushes: 6 total, peak 3 in a day. Pull requests: 5 total, peak 3 in a day. Issues: 29 total, peak 7 in a day. Comments: 38 total, peak 6 in a day. Stars: 341 total, peak 6 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

Recent activity

Latest issues, pull requests and releases

  • Pull request#120xwjahahahaha2026-01-21 09:48
  • Issue comment#102Zctoylm09272026-01-20 14:13
    finetuning on libero
  • Issue comment#85roychen19982025-10-28 03:41
    why 0% success when I run eval_rdt_mani
  • Issue comment#11818643638196xhx2025-10-18 15:26
    About finetune on maniskill data
  • Pull request#120xwjahahahaha2025-10-17 07:07
  • Pull request#107thkkk2025-09-28 02:45
  • Pull request#119thkkk2025-09-28 02:42
  • Pull request#119thkkk2025-09-28 02:35
  • Issue comment#76ketchup452025-09-25 08:58
    Fine-tuning on maniskill dataset with precomputed language embedding
  • Issue#118ketchup452025-09-22 07:43
    About finetune on maniskill data
  • Issue#117Agenda82025-09-11 11:54
    Clarification on reported mean ± std values in simulation results
  • Issue#116Luo-Zhongwei2025-09-03 09:06
    Reproducibility Issue: Performance degrades in sequential runs within a single script, but is stable across separate script executions
  • Issue#114mingyi-lee2025-09-01 12:11
    Request for URDF file
  • Issue comment#83jasper03142025-08-20 15:50
    applying RDT to widowx bridge Task in SimplerEnv, some pretraining details of RDT in bridgev2 dataset
  • Issue comment#102jasper03142025-08-19 13:22
    finetuning on libero
  • Issue#112DABINB2025-07-23 02:33
    Is there any issue with producer.py?
  • Issue comment#103csuastt2025-07-21 02:41
    Question about the fine-tuned checkpoint.
  • Issue comment#89Luo-Zhongwei2025-07-20 11:58
    Question about pretraining dataset
  • Issue comment#89J-Oyasumi2025-07-20 08:02
    Question about pretraining dataset
  • Issue comment#98Luo-Zhongwei2025-07-20 08:02
    How many the total tasks and episodes in rdt-ft-data for checking?
  • Issue#111Luo-Zhongwei2025-07-20 07:59
    so RDT train via 3 stage? here is my opinions
  • Issue comment#30Luo-Zhongwei2025-07-20 07:51
    Questions about open-source fine-tuning datasets
  • Issue comment#89Luo-Zhongwei2025-07-20 07:43
    Question about pretraining dataset
  • Issue comment#103Luo-Zhongwei2025-07-20 07:41
    Question about the fine-tuned checkpoint.
  • Issue comment#79chenyt312025-07-12 14:29
    After fine-tuning on my own dataset, the model performed poorly in the test set

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 341 stars here means stars gained during the window, not the repo's star count.