Ant Group uses action-free egocentric human videos to boost robot policy learning
antgroup · hf · 2026-11-17
Ant Group presents Ego Guidance, a mixture-of-transformers architecture that jointly predicts future visual states and actions for robot policy learning. A VLM backbone hosts an action expert trained on labeled robot data and a generation expert, while action-free human egocentric videos (cooking, crafts, everyday manipulation) contribute visual priors via cross-attention without requiring action labels, leveraging pretrained vision-language representations to improve policy learning.
More from Embodied
- ScaleVLA scales VLA models to 552B parameters: 10 demos beat 2B backbone trained on 50 — GalaxyGeneralRobotics · 2026-11-17
- ChipAgents CEO joins NYSE interview on chip AI expansion and chip superintelligence vision — WilliamWangNLP · 2026-11-17
- Nvidia Robotics Chief Says OpenAI's Astra Makes Robotic Training Data 100x Faster — pstAsiatech · 2026-11-17
- French-Japanese robotics AI conference maps gaps toward human-centric physical AI — FrnkNlsn · 2026-11-17
- VC Cao Guoxiong: PhysicalAI still in validation phase, embodied brain needs 5+ years — 创业邦 · 2026-11-17
- CoRL fireside chat: Fei-Fei Li and AMD CEO Lisa Su on stage together — PeterStone_TX · 2026-11-17