Podcast Episodes
Back to SearchScenes as Objects, Not Primitives: Instance-Structured 3D Tokenization
A feed-forward model that decomposes unposed images into instance-structured 3D token groups without annotations, enabling unified reconstruction, se…
2 months, 4 weeks ago
Current as Touch: Proprioceptive Contact Feedback for Compliant Dexterous Manipulation
A proprioceptive contact feedback method leveraging motor current signals as a touch proxy to enable compliant dexterous manipulation without dedicat…
3 months ago
DART: One-Shot VLA Policy Adaptation via Weight-Space Arithmetic
Uses weight-space arithmetic to isolate domain shifts from task knowledge, enabling one-shot VLA policy adaptation to new cameras or embodiments.
3 months ago
Does VLA Even Know the Basics? Act2Answer Benchmark
Introduces a benchmark showing VLAs lose 20–40 points in commonsense/world knowledge versus source VLMs after robotics fine-tuning, evaluated via act…
3 months ago
Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding
Learns dexterous manipulation policies that explicitly ground actions in generative contact predictions from visuotactile observations, improving rob…
3 months ago
Freeform Preference Learning (FPL) for Robotic Manipulation
Introduces multi-axis preference supervision to learn dense, language-conditioned rewards across speed/precision/subtask axes without segmentation; e…
3 months ago
Orca: The World is in Your Mind
Proposes a general world foundation model leveraging Next-State-Prediction to jointly generate text, images, and embodied actions within a unified fr…
3 months ago
Qwen-RobotNav: A Scalable Unified Navigation Model for Agentic Robotics
A unified 2B–8B parameter model for robot navigation tasks (VLN, ObjectNav, tracking, autonomous driving) via a configurable observation protocol, wi…
3 months ago
Scaling Robot Skills from Cheap Human Videos
Replaces noisy 6-DoF hand poses with relative wrist translation as a shared action space between humans and bimanual robots, enabling scalable skill …
3 months ago
ABC: An Open Behavior Cloning Stack for Bimanual Manipulation
Large-scale open-source framework for real-world robotic manipulation using behavior cloning, including the ABC-130K dataset with 3,500 hours and 130…
3 months ago