416 citations · 733 across the 25 of their papers we have counts for
28 papers
Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
Sixu Yan, Shikang Wang, Binhua Huang +11
This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands. Unlike existing VL…
UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
Yongkang Li, Lijun Zhou, Sixu Yan +11
Vision-Language-Action (VLA) models have recently emerged in autonomous driving, with the promise of leveraging rich world knowledge to improve the cognitive capabilities of drivin…
Mixture-of-Depths Attention
Lianghui Zhu, Yuxin Fang, Bencheng Liao +10
Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers…
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…
DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
Lunbin Zeng, Jingfeng Yao, Bencheng Liao +3
Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce…
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…
DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
Ziying Song, Lin Liu, Hongyu Pan +7
Most end-to-end autonomous driving methods rely on imitation learning from single expert demonstrations, often leading to conservative and homogeneous behaviors that limit generali…
Seed1.5-VL Technical Report
Dong Guo, Faming Wu, Feida Zhu +194
We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter v…
Fully Unified Motion Planning for End-to-End Autonomous Driving
Lin Liu, Caiyan Jia, Ziying Song +6
Current end-to-end autonomous driving methods typically learn only from expert planning data collected from a single ego vehicle, severely limiting the diversity of learnable drivi…
MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling
Yingyue Li, Bencheng Liao, Wenyu Liu +1
With the advancement of RNN models with linear complexity, the quadratic complexity challenge of transformers has the potential to be overcome. Notably, the emerging Mamba-2 has de…
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…
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…
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…
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
Lianghui Zhu, Zilong Huang, Bencheng Liao +4
Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT)…
MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning
Jialv Zou, Bencheng Liao, Qian Zhang +2
Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods…
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
Bo Jiang, Shaoyu Chen, Hao Gao +4
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. Existin…
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Lianghui Zhu, Bencheng Liao, Qian Zhang +3
Recently the state space models (SSMs) with efficient hardware-aware designs, i.e., the Mamba deep learning model, have shown great potential for long sequence modeling. Meanwhile…
MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
Bencheng Liao, Shaoyu Chen, Yunchi Zhang +5
High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in a…
VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
Shaoyu Chen, Yunchi Zhang, Bencheng Liao +7
High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for e…
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Bo Jiang, Shaoyu Chen, Qing Xu +7
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representat…
Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
Bencheng Liao, Shaoyu Chen, Bo Jiang +5
Online lane graph construction is a promising but challenging task in autonomous driving. Previous methods usually model the lane graph at the pixel or piece level, and recover the…