Zero-WAM: robots learn unseen tasks from a single human demo video, no fine-tuning
deepakpathak · x · 2026-08-28
Researchers from HKUST (GZ) and Robbyant present Zero-WAM, which treats a human demonstration video as an in-context prompt: the model watches how the scene should evolve and generates robot actions without task-specific fine-tuning.
- To train at scale, they built HumanGen, 74.2k generated human-robot pairs across 8.6k tasks.
- On 7 unseen RoboTwin tasks it hits 47.0% success, 29.5 points above the strongest video-action baseline, with real-robot transfer to unseen multi-object, long-horizon and insertion tasks.
Motivation: language says "put this there," but video also shows path, timing, contact order, and what "there" actually looks like.
Related event: Zero-WAM: Robots Learn New Tasks Zero-Shot from Human Video Prompts(5 posts)→
More from Embodied
- Musk teases next-gen Tesla Roadster unveil, hints at sub-1-second 0-60 mph — elonmusk · 2026-10-15
- Robotics papers on arXiv have grown ~6x in five years, peaking at 676 in a single week — Rewkang · 2026-10-15
- Bantam Tools launches HandWriter plotter inspired by legendary HP7475A — Merzmensch · 2026-10-15
- Amazon's Bee launches $74.99 Frontier wearable and $99.99 Eclipse smartphone recorder — The Verge AI · 2026-10-15
- Tesla plans to double Giga Berlin with 536,000 sqm hall; Cybercab and Optimus tipped for 2028 EU production — JOBhakdi · 2026-10-15
- China's AgiBot Reportedly Raising $210M at $7B Valuation, IPO May Slip to 2027 — xmercury_one · 2026-10-15