EgoTac: In-the-wild Tactile Prediction from Egocentric Vision
cs.CV, cs.RO
Submitted: 2026-08-15
Updated: 2026-10-16
Comments: NeurIPS 2026 Accepted. Project Page: https://egotac.github.io/
Project page: https://egotac.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Emergence of Human to Robot Transfer in Vision-Language-Action Models
- Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis
- Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
- DINOv2: Learning Robust Visual Features without Supervision
- OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
- HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction
- MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
- UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
- Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves
- EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models