From the 1 of 7 linked papers with an AI index.
7 papers
MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping
Heng Zhang, Kevin Yuchen Ma, Mike Zheng Shou +2
Cross-embodiment dexterous grasping aims to synthesize stable grasps across heterogeneous multi-fingered hands with little or no embodiment-specific tuning. Existing interaction-ce…
VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation
Mohan Liu, Zhihao Gu, Xuanyu Chen +5
VistaVLA is a two-stage framework that builds a geometry- and semantic-aware 3D cognitive map using Gaussian primitives and compresses it into compact tokens for vision‑language‑ac…
EAGOR: Embodied Reasoning in Omni-direction
Shriram Damodaran, Soumyaratna Debnath, Yan Wu +2
Omni-directional (360°) cameras provide embodied agents with a holistic view of their surroundings, making them suited for directional reasoning in tasks such as navigation and ob…
Semantic-Contact Fields for Category-Level Generalizable Tactile Tool Manipulation
Kevin Yuchen Ma, Heng Zhang, Weisi Lin +2
Generalizing tool manipulation requires both semantic planning and precise physical control. Modern generalist robot policies, such as Vision-Language-Action (VLA) models, often la…
NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control
Chia-Wen Chen, Yan Wu, Korrawe Karunratanakul +1
Achieving precise, versatile whole-body character control in physics-based animation remains challenging. Recent diffusion-based policies generate rich and expressive motions but t…
MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping
Heng Zhang, Kevin Yuchen Ma, Mike Zheng Shou +2
Dexterous grasping with multi-fingered hands remains challenging due to high-dimensional articulations and the cost of optimization-based pipelines. Existing end-to-end methods req…