Bencheng Liao

9

Papers

147

Total Citations

Papers (9)

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection