3 papers
cs.RO2026
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Jinhao Wu, Shiduo Zhang, Yicheng Liu +9
Most vision-language-action (VLA) models map observations directly to actions without explicit intermediate planning, which limits performance on long-horizon tasks where early mis…
cs.CV2025
Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving
Yunshen Wang, Yicheng Liu, Tianyuan Yuan +4
Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations…
cs.RO2025
Conditioning Matters: Training Diffusion Policies is Faster Than You Think
Zibin Dong, Yicheng Liu, Yinchuan Li +2
Diffusion policies have emerged as a mainstream paradigm for building vision-language-action (VLA) models. Although they demonstrate strong robot control capabilities, their traini…