Zhao-Heng Yin
Lead author of Mana, UC Berkeley / Amazon FAR researcher building scalable dexterous manipulation systems.
“Mana achieves zero-shot sim-to-real transfer — no real-world demonstration data was collected. The full pipeline generates training data in simulation, trains a visuomotor policy, and deploys directly on a physical Allegro hand.”
Source→“Mana achieves zero-shot sim-to-real transfer — no real-world demonstration data was collected... achieves roughly 70% success rates across grasping and in-hand manipulation on four distinct tool categories.”
Source→“The paper lists Amazon FAR (Fundamental AI Research) as a co-affiliation of all four authors (title page). This is an Amazon-affiliated research output, signaling Amazon's investment in dexterous physical AI capabilities.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.