Podcast Episodes
Back to SearchVERA: Video-to-Action World Model Policy
A 14B-parameter video world model that converts predicted visual futures into embodiment-agnostic actions via Jacobian inverse-dynamics, enabling zer…
3 months, 1 week ago
GEN-1: Scaled Dexterous Manipulation Foundation Model
A dexterous manipulation foundation model trained on 500k hours of real-world bimanual data that handles deformable objects such as cardboard folding…
3 months, 1 week ago
Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation
Develops an SE(3)-equivariant flow-based visuomotor policy leveraging spherical harmonics for efficient and geometrically consistent robot manipulati…
3 months, 2 weeks ago
Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
Introduces a dual-stream transformer architecture inspired by cortical visual processing for learning robotic manipulation policies.
3 months, 2 weeks ago
VisualClaw: A Self-Evolving Wearable Vision Agent
An edge-filtered video streaming agent that evolves skills from memory and runs on smart glasses, reducing API costs by 98%, accompanied by the Visua…
3 months, 2 weeks ago
Kairos: A Native World Model Stack for Physical AI
A 4B unified architecture for world understanding, generation, and action with hybrid linear attention enabling real-time edge inference across embod…
3 months, 2 weeks ago
DragMesh-2: A Contact-Driven Framework for Dexterous Hand–Object Interaction
A framework that trains a 51-DoF dexterous hand to open drawers and doors using only physical contact without requiring tactile sensors.
3 months, 2 weeks ago
Guava: A Universal Harness for Robot Manipulation
A 4B open-source VLA-style model trained on fewer than 2K simulation trajectories that matches closed frontier systems on real-world manipulation tas…
3 months, 2 weeks ago
Geometric Action Model for Robot Policies
A new geometric action model for robot manipulation policies that focuses on structured action representations to improve policy learning and general…
3 months, 2 weeks ago
ENPIRE: Physical AutoResearch with a Fleet of 8 Robots
ENPIRE demonstrates fully autonomous physical AutoResearch where Codex agents control a fleet of 8 robots overnight, self-improving through real hard…
3 months, 2 weeks ago