270 citations · 591 across the 48 of their papers we have counts for
52 papers
Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization
Zhiyuan Ma, Jiaming Li, Lingzhen Li +7
Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. However, reward-maximizing RL…
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Xin Zhou, Zongchuang Zhao, Zhibo Yang +13
We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of the pretrained vision-langu…
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
Hengyi Xie, Chenfei Yao, Xianjin Wu +4
Vision-language-action (VLA) models commonly adopt an LLM-centric pathway, processing visual observations and language instructions through a large language model b…
Wat3R: Underwater 3D Geometry Learning without Annotations
Jiangwei Ren, Xingyu Jiang, Zijie Song +4
Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pion…
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Xin Zhou, Dingkang Liang, Xiwu Chen +4
Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene gen…
PointTPA: Dynamic Network Parameter Adaptation for 3D Scene Understanding
Siyuan Liu, Chaoqun Zheng, Xin Zhou +3
Scene-level point cloud understanding remains challenging due to diverse geometries, imbalanced category distributions, and highly varied spatial layouts. Existing methods improve…
ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
Yiran Guan, Sifan Tu, Dingkang Liang +6
Omni-modal reasoning is essential for intelligent systems to understand and draw inferences from diverse data sources. While existing omni-modal large language models (OLLM) excel…
Towards Generalizable Robotic Manipulation in Dynamic Environments
Heng Fang, Shangru Li, Shuhan Wang +3
Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap primarily stems from a scarcity of d…
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
Yiran Guan, Liang Yin, Dingkang Liang +5
Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synch…
MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
Haoyu Fu, Diankun Zhang, Zongchuang Zhao +7
Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and…
Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
Dingkang Liang, Cheng Zhang, Xiaopeng Xu +3
Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datase…
NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
Wei Xu, Cheng Wang, Dingkang Liang +4
Underwater exploration offers critical insights into our planet and attracts increasing attention for its broader applications in resource exploration, national security, etc. We s…
More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
Hongkai Lin, Dingkang Liang, Mingyang Du +2
Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, p…
SoccerNet 2025 Challenges Results
Silvio Giancola, Anthony Cioppa, Marc Gutiérrez-Pérez +115
The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understandi…
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
Linghao Zhu, Yiran Guan, Dingkang Liang +6
Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM). However, current…
Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
Xin Zhou, Dingkang Liang, Kaijin Chen +7
Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, prima…
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving
Zongchuang Zhao, Haoyu Fu, Dingkang Liang +5
The Large Visual-Language Models (LVLMs) have significantly advanced image understanding. Their comprehension and reasoning capabilities enable promising applications in autonomous…
SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting
Dongliang Luo, Hanshen Zhu, Ziyang Zhang +4
Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text s…
ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation
Haoyu Fu, Diankun Zhang, Zongchuang Zhao +7
End-to-end (E2E) autonomous driving methods still struggle to make correct decisions in interactive closed-loop evaluation due to limited causal reasoning capability. Current metho…
A Unified Image-Dense Annotation Generation Model for Underwater Scenes
Hongkai Lin, Dingkang Liang, Zhenghao Qi +1
Underwater dense prediction, especially depth estimation and semantic segmentation, is crucial for gaining a comprehensive understanding of underwater scenes. Nevertheless, high-qu…
UniFuture: A 4D Driving World Model for Future Generation and Perception
Dingkang Liang, Dingyuan Zhang, Xin Zhou +7
We present UniFuture, a unified 4D Driving World Model designed to simulate the dynamic evolution of the 3D physical world. Unlike existing driving world models that focus solely o…
The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey
Sifan Tu, Xin Zhou, Dingkang Liang +4
The Driving World Model (DWM), which focuses on predicting scene evolution during the driving process, has emerged as a promising paradigm in the pursuit of autonomous driving (AD)…
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Xin Zhou, Dingkang Liang, Sifan Tu +6
Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to inc…
MINIMA: Modality Invariant Image Matching
Jiangwei Ren, Xingyu Jiang, Zizhuo Li +3
Image matching for both cross-view and cross-modality plays a critical role in multimodal perception. In practice, the modality gap caused by different imaging systems/styles poses…