3 papers
cs.CV2026
DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model
Jingke Wang, Zhenru Zhao, Shuangming Lei +8
Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow language guidances. However,…
cs.CV2026
StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention
Zhongrui Yu, Zhao Wang, Yijia Xie +4
Feedforward reconstruction is crucial for autonomous driving applications, where rapid scene reconstruction enables efficient utilization of large-scale driving datasets in closed-…
cs.RO2025
SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning
Yuhang Lin, Yijia Xie, Jiahong Xie +5
Generating physically realistic humanoid-object interactions (HOI) is a fundamental challenge in robotics. Existing HOI generation approaches, such as diffusion-based models, often…