VITAL: From Visual Motion to Precise Action
cs.CV
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: Technical Report; 37 pages, 14 figures, 19 tables; Project Page at https://worldbench.github.io/vital GitHub at https://github.com/worldbench/VITAL
Code: https://github.com/worldbench/VITAL
Project page: https://worldbench.github.io/vital
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- From Imitation to Refinement -- Residual RL for Precise Assembly
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
- DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
- Genie: Generative Interactive Environments
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Pseudo-Simulation for Autonomous Driving
- WorldVLA: Towards Autoregressive Action World Model
- Beyond Reconstruction: What Matters in Action Tokenization for Robot Policies?
- CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
- Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
- DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving
- NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
- Behavior-Aligned Action Tokenization for Robot Policy Learning
- Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
- Language-Conditioned World Modeling for Visual Navigation
- One Step Diffusion via Shortcut Models
- Mean Flows for One-step Generative Modeling
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