RoboDojo Scores 32 of 34 Robot Policies Under 10% Success
SubscribeSign in
RoboDojo Scores 32 of 34 Robot Policies Under 10% Success<br>The model at the top has zero downloads. It also reports 98.9% on LIBERO.<br>Jay Chia<br>Aug 20, 2026
Share
Someone else ran the numbers
Every VLA paper reports its own benchmark table, using its own benchmark, run by the people who trained the model. RoboDojo is the other thing. 42 simulation tasks and 18 real ones, run by the MMLab@HKU and Tsinghua group that built it. One published evaluation-integrity protocol, and 34 policies ranked on one page.<br>The distribution is the story. G0.5 leads at 14.88% success, Xiaomi-Robotics-1 is second at 13.93%, and Tencent’s Hy-Embodied-0.5-VLA third at 8.80%. That is the entire top of the table. π0.5 comes fifth at 6.91%, GR00T-N1.7 twentieth at 1.31%, and OpenVLA-OFT last at 0.02%. Thirty-two of the 34 sit in single digits, and the two that clear it do so by four points.
Set that against what the same models report on LIBERO, where 95% and up is now unremarkable. Both numbers are real. The gap between them says how much of a reported success rate belongs to the benchmark rather than the policy. You can only see it when one group runs everything under one protocol. Two caveats before you quote it. The labs submitted the top three themselves, and the RoboDojo team ran most of the rest. RoboDojo is also deliberately hard.<br>Then there is the leader. π0.5 and most current VLAs bolt a flow-matching action expert onto a VLM. G0.5 drops it and keeps the VLM as the actor. One decoder from Qwen3.5-2B emits reasoning and action tokens in a single stream, and a learned codec maps 14 embodiments into one 27-dimensional action space. Galaxea reports 76.7% on its own R1-Lite and R1-Pro hardware against 53.3% for π0.5, and now has an outside leaderboard agreeing on the ranking.<br>Its weights have been public since 16 June. The repository shows zero downloads . The license is non-commercial, which explains most of it. Check it before you read that leaderboard as a recommendation.<br>Thanks for reading Topic Queue! Subscribe for free to receive new posts and support my work.
Subscribe
Research
ACE-Data-0 is downloadable now, and you cannot ship with it
ACE-Data-0 is downloadable as of 17 August: 24,810 files, mostly video and parquet, with per-session IMU and audio on the room-scale takes. The access gate came off with it, so no request needed.<br>The license is where it stops. It is a bespoke ace-data-0-research-license, so you can read this data and not ship with it. viewer: false means you cannot inspect it before downloading either. If you checked the repo in early August and found it empty, look again.<br>XPolicyLab cuts a policy integration from five hours to thirty minutes
Connecting N policies to M evaluation environments normally costs N times M integrations. Every model brings its own dependencies, data layout, and runtime interface. XPolicyLab gets that down to N plus M. It fixes shared observation, action, and trajectory schemas plus one small adapter interface. Policy inference and environment execution run as separate processes, so each side keeps its own stack.<br>Wiring up one representative policy took over five hours without the standard, two hours conforming to it, and thirty minutes with the packaged agent skills. Forty-two policies are adapted already. If you maintain your own evaluation harness, read the adapter layout before you extend it again.<br>Action chunking works, but not for the reason usually given
Predicting a sequence of actions and executing a prefix open-loop is what ACT is named for, and most recent VLAs do it too. The reasons usually given are compounding error, absorbing inference latency, and smoothing motion. A new paper from Russ Tedrake’s group tests those and lands elsewhere. Long open-loop prefixes mostly let a short-context policy imitate non-Markovian demonstrations. That means the expert acted on history the policy cannot see. Across four simulation tasks and two real ones, expert non-Markovianity shaped the relationship between success and open-loop horizon. Compounding error mattered less.<br>Give the policy enough context, and the effect disappears. The most reactive closed-loop version then performs best. Put that next to the dexterity pre-training paper below, which ablates short action chunks for reactive control and points the same way. If you arrived at your open-loop horizon by sweeping it, that horizon may be measuring your demonstration data rather than your policy. Lengthening the context window is the experiment that tells you which.<br>HiPHI publishes 600 hours of sub-millimeter motion capture
HiPHI landed on the Hub during the World Robot Conference: optical motion capture at 90 Hz with sub-millimeter marker tracking, from 132 performers. On the interaction half, the rig captures each object’s mesh and 6-DoF trajectory in sync. Cross-dataset joint error falls steadily from 3 hours of training data up to 300,...