Xiaosong Jia

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

TrajTok: What makes for a good trajectory tokenizer in behavior generation?

Revisiting Standard-Definition Map Based Motion Prediction in the Era of End-to-End Autonomous Driving

ReGen4AD: Retrieval Based Online Video Generation for Reactive Autonomous Driving Simulation

PointARSim: Point-cloud–enhanced Generative Auto-Regressive Simulation for Closed-loop End-to-end Autonomous Driving Evaluation

Understanding the Task and Data Misconceptions in Online Map Based Motion Prediction for Autonomous Driving and a Boundary-Free Baseline

FlashPlanner: Accelerating Diffusion-based Planner for Autonomous Driving via Globally Consistent Velocity Field and Redundancy Reduction

ReSim: Reliable World Simulation for Autonomous Driving

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving

ESDMotion: End-to-end Motion Prediction Only with SD Maps

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving