Vision-Language-Action-Model

EMMA: End-to-End Multimodal Model for Autonomous Driving

MotionLM: Multi-Agent Motion Forecasting as Language Modeling

TRAJEGLISH: TRAFFIC MODELING AS NEXT-TOKEN PREDICTION

SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

DIFFUSION-BASED PLANNING FOR AUTONOMOUS DRIVING WITH FLEXIBLE GUIDANCE

Robust Autonomy Emerges from Self-Play

VLM-R1: A stable and generalizable R1-style Large Vision-Language Model

ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills