[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
active 2025-05-26 → 2026-07-06 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 407 days from 2025-05-26 to 2026-07-06. Pushes: 5 total, peak 3 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 46 total, peak 3 in a day. Comments: 64 total, peak 4 in a day. Stars: 773 total, peak 72 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| zhan72 | 21 | 1 | 2 | 13 |
| Boltzmachine | 8 | 0 | 0 | 2 |
| zchoi | 5 | 0 | 0 | 2 |
| BroJunn | 5 | 0 | 0 | 3 |
| ningding97 | 4 | 4 | 0 | 0 |
| OrangeSodahub | 4 | 0 | 0 | 4 |
| Louis-ZhangLe | 3 | 0 | 0 | 3 |
| ybpy | 3 | 0 | 0 | 0 |
| zimgong | 3 | 0 | 1 | 1 |
| lzqbuaaer | 2 | 0 | 0 | 2 |
| chenkang455 | 2 | 0 | 0 | 1 |
| CreativeLuo | 2 | 0 | 0 | 1 |
| llliuxiao | 2 | 0 | 0 | 1 |
| 2561681244 | 2 | 0 | 0 | 2 |
| dreamcubeblock | 2 | 0 | 0 | 1 |
| lozoRUST | 2 | 0 | 0 | 1 |
| lck1201 | 2 | 0 | 0 | 2 |
| yuyu5333 | 2 | 0 | 0 | 1 |
| FengRobotics | 1 | 0 | 0 | 0 |
| WangDaChui627 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#55Muksaki2026-02-06 01:46Memory lease
- Issue#70123123qqqqdqd2025-12-27 11:31Do we need to train different models for different tasks?
- Issue comment#15ShimBoi2025-12-25 05:16Datasets
- Issue#69Tianchong-Jiang2025-12-18 21:48LIBERO RL checkpoints
- Issue comment#45zhide7302025-12-16 13:20AttributeError: module 'transformers_modules.Openvla-oft-SFT-libero10-trajall.processing_prismatic' has no attribute 'PrismaticProcessor'
- Issue comment#5725616812442025-12-14 12:29TensorFlow was not built with CUDA kernel binaries compatible with compute capability 9.0. CUDA kernels will be jit-compiled from PTX, which could take 30 minutes or longer
- Issue comment#49liruiluo2025-12-11 07:37微信群失效了，可以再发一下加群码吗？
- Issue comment#65OrangeSodahub2025-12-08 08:02NUM_GPUS
- Issue comment#6525616812442025-12-08 07:48NUM_GPUS
- Issue comment#65OrangeSodahub2025-12-08 07:43NUM_GPUS
- Issue comment#65OrangeSodahub2025-12-08 06:06NUM_GPUS
- Issue comment#55OrangeSodahub2025-12-07 12:53Memory lease
- Issue comment#25Jeff-i-Programme2025-11-25 02:55tarj1和trajall模型训练问题
- Issue#64jycao0002025-11-07 14:08The WeChat group QR code has expired.
- Issue#61justzhanghy2025-11-04 11:43Piper two-arm SFT model
- Issue comment#59lck12012025-11-04 06:40几个关于paper的细节问题
- Issue comment#59lck12012025-11-04 04:10两个关于implementation的细节问题
- Issue comment#30Iron-Wph2025-10-31 08:45ray.exceptions.OutOfMemoryError: Task was killed due to the node running low on memory
- Issue comment#36JiaaZheng2025-10-30 12:29LoRA support?
- Issue comment#1youmo4452025-10-26 11:48Installation Issue
- Issue comment#49lucywang7202025-10-23 16:35微信群失效了，可以再发一下加群码吗？
- Issue#56anshks2025-10-22 21:32OpenVLA-OFT pretrained checkpoint
- Issue#55lozoRUST2025-10-18 07:59Memory lease
- Issue comment#53lozoRUST2025-10-18 03:21Torch conflict between openvla-oft and verl
- Issue comment#51AnonAnonAnonAnonAnon2025-10-16 08:42where is the released model based on RL training?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 773 stars here means stars gained during the window, not the repo's star count.