Qian Zhang

ReDrive: Shaping Representations with World Modeling for End-to-End Driving

Yueting Zhu, Shaoyu Chen, Yuehao Song +4

Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception…

Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation

Yueting Zhu, Yuehao Song, Kaicheng Zhang +5

Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming…

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

Hao Gao, Shaoyu Chen, Yifan Zhu +4

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-ba…

Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning

Yuehao Song, Shaoyu Chen, Hao Gao +8

Vision-language models (VLMs) enhance the planning capability of end-to-end (E2E) driving policy by leveraging high-level semantic reasoning. However, existing approaches often ove…

DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving

Jialv Zou, Shaoyu Chen, Bencheng Liao +6

Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive empl…

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…

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…

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

Jialv Zou, Bencheng Liao, Qian Zhang +2

Recent advancements in unified multimodal understanding and visual generation (or multimodal generation) models have been hindered by their quadratic computational complexity and d…

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

Bo Jiang, Shaoyu Chen, Qian Zhang +2

OpenAI o1 and DeepSeek R1 achieve or even surpass human expert-level performance in complex domains like mathematics and science, with reinforcement learning (RL) and reasoning pla…

cs.CV2025★ 1 cited

SenseExpo: Spatial Exploration and Navigation via Scene Estimation from Expeditious Predictive Operators

Haojia Gao, Haohua Que, Mingkai Liu +9

We present \textbf{SenseExpo}, a lightweight single-robot exploration framework that integrates a compact map prediction network into a frontier-based strategy. SenseExpo addresses…

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…

Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

Bo Jiang, Shaoyu Chen, Bencheng Liao +6

End-to-end autonomous driving demonstrates strong planning capabilities with large-scale data but still struggles in complex, rare scenarios due to limited commonsense. In contrast…

cs.CV2024★ 1 cited

Occupancy as Set of Points

Yiang Shi, Tianheng Cheng, Qian Zhang +2

In this paper, we explore a novel point representation for 3D occupancy prediction from multi-view images, which is named Occupancy as Set of Points. Existing camera-based methods…

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

Bencheng Liao, Xinggang Wang, Lianghui Zhu +2

Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer F…