Podcast Episodes
Back to SearchDexMachina: RL for Long-Horizon Bimanual Dexterous Policies
An RL algorithm that learns long-horizon bimanual dexterous policies for any robot hand from a single human demonstration, emphasizing generalization…
2 months, 3 weeks ago
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
A unified platform comprising GE-Base (video diffusion model trained on 1M+ manipulation episodes), GE-Act (flow-matching action model), and GE-Sim (…
2 months, 3 weeks ago
RoboTTT: Test-Time Training for Visuomotor Policies
Introduces test-time training (TTT) inside the policy to natively scale visuomotor context to 8K timesteps at constant inference cost, enabling one-s…
2 months, 3 weeks ago
HY-Embodied-VLM-1.0: Efficient Physical-World Agents
An embodied vision-language-action model with released weights, code, and paper targeting robotic manipulation and embodied AI tasks.
2 months, 3 weeks ago
Learning Unified Force and Position Control for Legged Loco-Manipulation
Introduces a unified RL policy that jointly handles force and position control on quadrupedal and humanoid robots without force sensors, enabling pos…
2 months, 3 weeks ago
HapticVLA: Extending Vision-Language-Action Models to Contact-Rich Tasks Without Touch Sensors
Enables contact-rich robotic manipulation using a VLA model trained with tactile sensing data but requiring no tactile input at inference time. Disti…
2 months, 3 weeks ago
AnoleVLA: Lightweight VLA with Deep State Space Models for Mobile Manipulation
Proposes a lightweight VLA model leveraging deep state space models (SSMs) instead of transformers for efficient mobile manipulation. Targets resourc…
2 months, 3 weeks ago
ABot-N1: Visual Language Navigation Foundation Model
Decouples cognition from control in a VLM-based navigation policy, delivering 35% POI arrival gains and over 92% success rates in complex indoor and …
2 months, 3 weeks ago
ABot-AgentOS: A General-Purpose Robotic Agent Operating System
Provides scene-conditioned planning, context-isolated skill execution, multi-modal memory, and self-evolution capabilities for long-horizon embodied …
2 months, 3 weeks ago
Trust Region Policy Distillation (TOP-D)
Transforms unstable on-policy distillation into a stable training paradigm via dynamic proximal teacher construction, improving sample efficiency wit…
2 months, 3 weeks ago