FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity
cs.RO
Submitted: 2026-10-13
Updated: 2026-10-13
Project page: https://fact-1-0.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- R3M: A Universal Visual Representation for Robot Manipulation
- DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation
- EgoMimic: Scaling Imitation Learning via Egocentric Video
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- 3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing
- Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
- ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation
- RT-H: Action Hierarchies Using Language
- Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
- Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
- Cosmos World Foundation Model Platform for Physical AI
- TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks
- Wan: Open and Advanced Large-Scale Video Generative Models
- UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies