VidAct: Learning Manipulation from In-the-Wild Videos with Object-Centric 3D Awareness
cs.RO
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Emergence of Human to Robot Transfer in Vision-Language-Action Models
- EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
- DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
- DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
- FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Models
- LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior
- QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
- SAM 3D: 3Dfy Anything in Images
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
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving