Hongsong Wang

RGS: A Unified Representation-Generation-Selection Framework for Knowledge-Based Visual Question Answering

PrismAD: Decoupled Planning via Semantic Mixture-of-Planners for End-to-End Autonomous Driving

This letter presents PrismAD, a decoupled end-to-end autonomous driving framework based on a Semantic Mixture-of-Planners that exhibits competitive performance on the nuScenes open-loop dataset and NeuroNCAP closed-loop benchmark.

AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning

AnchorVLA is proposed, a hierarchical decision-anchored VLA planning framework that uses trajectory-pattern anchors as an explicit interface between high-level VLA reasoning and continuous trajectory execution and preserves LLM-based decision making while improving inference efficiency, semantic-action alignment, and c...