Skip to content

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

Python · active 2026-01-282026-08-07 (UTC)

Complete coverage26,440 / 26,440 hourly files (100%) · 2 absent upstream2023-08-152026-08-20 (UTC)
Events
592
Pushes
27
Pull requests
6
Issues
18
Stars
494
Forks
27

Activity over time

Daily event counts in the loaded window

Line chart, 192 days from 2026-01-28 to 2026-08-07. Pushes: 27 total, peak 7 in a day. Pull requests: 6 total, peak 2 in a day. Issues: 18 total, peak 2 in a day. Comments: 15 total, peak 2 in a day. Stars: 494 total, peak 98 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#77CharioteerStark2026-06-04 22:32
  • Issue#7224607079252026-05-24 09:52
    Question on 1-Step Inference Logic in DreamZero-Flash
  • Issue comment#56suixin14242026-05-22 12:44
    How long will it take for finetune?
  • Pull request#69parrot182026-05-01 12:32
  • Issue#63DafengChi2026-04-20 03:02
    Wan2.1-I2V-5B-480P
  • Issue#46seonghyeonye2026-04-19 06:52
    Question: Why does `test_client_AR.py` send 4 frames per chunk instead of 8?
  • Issue comment#46seonghyeonye2026-04-19 06:52
    Question: Why does `test_client_AR.py` send 4 frames per chunk instead of 8?
  • Issue comment#42seonghyeonye2026-04-19 06:41
    [Question] Possible incorrect architecture specs for Wan2.1-I2V-14B in comparison table
  • Issue#32seonghyeonye2026-04-19 06:26
    Clarification on 7Hz inference frequency: per-chunk or per-action?
  • Issue#61boqian-li2026-04-16 18:29
    State token attention mismatch between training and inference
  • Issue#58ShuaiZhou3022026-04-15 06:00
    Training steps / schedule for new-embodiment (YAM) fine-tuning in the paper vs. released scripts
  • Issue#50Undefinedx-Zhang2026-04-01 03:03
    Question regarding the specific benchmarks used on the MolmoSpaces leaderboard
  • Issue comment#31Undefinedx-Zhang2026-04-01 02:58
    Any plan to release a flash-version of 5B checkpoint?
  • Issue comment#449293622642026-03-25 01:34
    About how to identify the instruction is done
  • Issue comment#43NVshawnhwang2026-03-24 22:48
    error with batch size > 1
  • Issue comment#34NValec2026-03-18 22:18
    no experiment_cfg in AgiBot ckpt
  • Issue#21joeljang2026-03-18 18:24
    How to generate longer predictive video?
  • Issue#35joeljang2026-03-18 18:19
    How to set up simulation-based evaluation baselines without real robot hardware?
  • Issue#34Megan-Jiang2026-03-17 06:40
    no experiment_cfg in AgiBot ckpt
  • Issue#31whyxz2026-03-16 06:35
    Any plan to release a flash-version of 5B checkpoint?
  • Issue comment#26joeljang2026-03-10 23:21
    Fix Sim Eval Error
  • Issue#25Loki-Lu2026-03-10 02:54
    RuntimeError: Broadcasting dimension mismatch in action loss computation when batch_size > 1
  • Issue comment#19Chunchunyoyo2026-03-05 06:23
    flash-attn can only support torch 2.5cxx max
  • Issue comment#17joeljang2026-03-01 07:18
    DREAMZERO-AgiBot checkpoint
  • Issue#19persuer02026-02-28 06:24
    flash-attn can only support torch 2.5cxx max

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 494 stars here means stars gained during the window, not the repo's star count.