5 papers
InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
Hongyuan Tao, Bencheng Liao, Shaoyu Chen +4
Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they of…
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
Zhiyu Zheng, Shaoyu Chen, Haoran Yin +5
End-to-end autonomous driving (E2EAD) systems, which learn to predict future trajectories directly from sensor data, are fundamentally challenged by the inherent spatio-temporal im…
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
Hao Gao, Shaoyu Chen, Bo Jiang +11
Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and an open-loop gap.…
DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
Bencheng Liao, Shaoyu Chen, Haoran Yin +8
Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capabi…
Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation
Bencheng Liao, Hongyuan Tao, Qian Zhang +5
Recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance but face deployment challenges due to their quadratic computational complexity, growing Key-Val…