Huaiyu Wan

Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate

Multi-Agent Debate (MAD) improves the reasoning performance of Large Language Models (LLMs) through multi-round interaction. However, LLMs in MAD are highly susceptible to blind conformity. Existing individual evaluation methods, typically based on confidence or perplexity, fail to reflect the correctness of reasoning...

TrajAR: Long-Term Trajectory Prediction at Urban Intersections via Multi-scale Interaction Perception

Low-Rank Prior-Induced Consistency Flow Matching for Efficient Traffic Imputation

Low-Rank Prior-Induced Consistency Flow Matching (LOFT) is proposed for efficient and effective distribution modeling under highly sparse data, and introduces an uncertainty-aware rectification mechanism to enable efficient inference by linearizing generative trajectories.

G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction

G-VTM, a generalized vision-trajectory model, is proposed, which captures global map semantics while modeling scenario-and direction-aware interaction based on intuitive visual perception and achieves strong generalized performance under heterogeneous traffic conditions.

Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?

DynaSTar is proposed, a Dynamic Spatio-Temporal Graph Invariant Learning model designed for reliable out-of-time (OOT) traffic prediction under evolving topologies, which employs a dynamic probabilistic graph structure, which is continuously refined through momentum-based updates and differentiable sparse sampling to m...

Low-Rank Prior-Induced Consistency Flow Matching for Efficient Traffic Imputation

Low-Rank Prior-Induced Consistency Flow Matching (LOFT) is proposed for efficient and effective distribution modeling under highly sparse data, and introduces an uncertainty-aware rectification mechanism to enable efficient inference by linearizing generative trajectories.