Hanming Deng

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

BridgEAD: A Vision-Language Framework for Action Modeling in End-to-End Autonomous Driving

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving