Podcast Episodes
Back to SearchLocal Policies Enable Zero-shot Long-Horizon Manipulation
Proposes training local policies in simulation that transfer zero-shot to real-world long-horizon robotic manipulation tasks. Addresses the challenge…
2 months, 2 weeks ago
Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids
Trains perception-driven dexterous manipulation policies in simulation for zero-shot real-world transfer on humanoid robots. Focuses on bridging the …
2 months, 2 weeks ago
UniTracker: A Universal Motion Tracking Framework for Humanoid Robots
A framework enabling humanoid robots to execute diverse motions within physical limits, with video demonstrations and open-source code. Targets gener…
2 months, 2 weeks ago
ViTacFormer: Dexterous Manipulation via Active Vision and High-Resolution Touch Sensing
A pipeline combining active vision and high-resolution tactile sensing for dexterous manipulation on high-DoF robot hands, achieving approximately 2.…
2 months, 2 weeks ago
Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language
Uses language and demonstrations to learn which aspects of behavior matter for reward in imitation learning, enabling 5× faster learning by avoiding …
2 months, 2 weeks ago
FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
Steers frozen robot foundation models including VLAs, diffusion policies, and world models using human corrections via action inversion in latent spa…
2 months, 2 weeks ago
RoboTTT: End-to-End Robotic Assembly with Test-Time Training
Presents a single end-to-end policy that performs precise, unscripted assembly of complex objects, measuring every grasp and alignment without speed-…
2 months, 2 weeks ago
Xiaomi-Robotics-U0: A 38B World-Foundation Model for Unified Embodied Perception and Synthesis
38B autoregressive world foundation model unifying text-to-image, multi-view scene generation, embodied transfer, and video generation; ranks #1 on W…
2 months, 2 weeks ago
SpatialPoint: Spatial-Aware Point Prediction for Embodied Localization
A spatial-aware point prediction method for embodied localization tasks. Addresses grounding and spatial reasoning in embodied AI settings.
2 months, 2 weeks ago
Multi-AUV Scene-Adaptive Embodied Intelligence for Multi-Target Tracking
An embodied AI framework for multi-AUV (Autonomous Underwater Vehicle) multi-target tracking in ad-hoc underwater networks. Incorporates scene-adapti…
2 months, 2 weeks ago