4 papers
GRID-Planner: Graph-Structured Relational Reward Shaping for Diffusion Planning
Zhao Yang, Zezhong Qian, Yinan Shi +2
Autonomous driving planning requires selecting trajectories that remain safe, rule-compliant, and comfortable under complex multi-agent interactions, yet robust closed-loop decisio…
ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning
Zhao Yang, Yinan Shi, Mingyuan Yao +3
Vision-language action (VLA) models increasingly adopt chunked action heads to satisfy real-time constraints; however, this introduces boundary jitter: overlapping regions between…
DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusion
Haoteng Li, Zhao Yang, Zezhong Qian +5
Accurate and high-fidelity driving scene reconstruction relies on fully leveraging scene information as conditioning. However, existing approaches, which primarily use 3D bounding…
DualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward Guidance
Zhao Yang, Zezhong Qian, Xiaofan Li +5
Accurate and high-fidelity driving scene reconstruction demands the effective utilization of comprehensive scene information as conditional inputs. Existing methods predominantly r…