Zero-WAM Lets Robots Learn Tasks from Human Videos
CyberRobooo · x · 2026-08-29
Robbyant's Zero-WAM explores In-Context Learning for robots. Their HumanGen pipeline generated 74.2K human-robot ICL pairs. To prevent cheating, they designed In-Context Future Chunk Prediction (IFP), forcing the model to predict actions based on human videos. Zero-WAM achieved 46.95% success on unseen tasks, significantly outperforming baselines.
Related event: Zero-WAM: Robots Learn New Tasks Zero-Shot from Human Video Prompts(5 posts)→
More from Embodied
- SEAR: first large-scale controlled study of self-evolving robot agents, 7 LLMs, 330 tasks — xiye_nlp · 2026-10-16
- Podcast: subsea robotics startup Ulysses on operating 1,500m underwater and ocean carbon — blakemenezes · 2026-10-16
- Sony unveils $5,900 gold-plated Walkman with AI music enhancement — Polymarket · 2026-10-16
- ROBIB Meetup #3 returns to Ghent on Nov 19 with Physical AI talks, demos and panel — MarwaEldiwiny · 2026-10-16
- VLX-Go: Multi-Stage Vision-Language Training Boosts Robot Person-Following Among Distractors — omlab · 2026-10-16
- Ledger Atom Debuts as Agent-Approval Security Device; Critic Says a $100 iPhone 8 Beats It — adamamcbride · 2026-10-16