3 papers
cs.CV2026
Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving
Tian Zhang, Zhuo Huang, Hongrui Ye +3
Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO), making trajectory selection cr…
cs.CV2026
Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous Driving
Xuyang Chen, Conglang Zhang, Chuanheng Fu +9
Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explicit intermediate representations t…
cs.CV2025
MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion
Xuyang Chen, Zhijun Zhai, Kaixuan Zhou +8
Mesh models have become increasingly accessible for numerous cities; however, the lack of realistic textures restricts their application in virtual urban navigation and autonomous…