Podcast Episodes
Back to SearchSpeedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
Proposes a plug-and-play policy module designed to accelerate existing embodied manipulation policies without retraining them from scratch.
2 months, 2 weeks ago
R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation
Introduces a real-time 3D-aware policy framework for embodied manipulation tasks, enabling spatially grounded action generation.
2 months, 2 weeks ago
VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation
Presents a vision-language-action model grounded in 3D Gaussian representations that integrates geometric and semantic awareness for improved robotic…
2 months, 2 weeks ago
SKooP: Symmetric Koopman Predictions for Legged Robot Reinforcement Learning
Leverages symmetric Koopman operator predictions within a reinforcement learning framework to achieve faster training and better generalization for l…
2 months, 2 weeks ago
RobotTT: A Tactile Transformer for Dexterous Manipulation
A tactile foundation model and sim-to-real pipeline designed for dexterous manipulation tasks. Combines transformer-based tactile sensing with a sim-…
2 months, 2 weeks ago
TAC-LOCO: Unified Whole-Body Control for Contact-Aware Locomotion and Manipulation
A tactile-informed whole-body loco-manipulation controller for quadrupedal robots that unifies locomotion and manipulation using tactile sensing. Ena…
2 months, 2 weeks ago
TACTIC: Contact-Centric Control for Whole-Arm Manipulation
A contact-centric whole-arm manipulation framework that conditions control on both tactile and visual inputs. Targets dexterous manipulation tasks re…
2 months, 2 weeks ago
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLAs
SIEVE introduces structure-aware data selection specifically for imitation learning with Vision-Language-Action models, aiming to improve training ef…
2 months, 2 weeks ago
DexMachina: 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, 2 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, 2 weeks ago