中文
相关论文

相关论文: DriveDreamer-2: LLM-Enhanced World Models for Dive…

200 篇论文

How do video understanding models acquire their answers? Although current Vision Language Models (VLMs) reason over complex scenes with diverse objects, action performances, and scene dynamics, understanding and controlling their internal…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Alexandros Stergiou

Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Zhiyu Tan , Hao Yang , Luozheng Qin , Jia Gong , Mengping Yang , Hao Li

Simulation frameworks have been key enablers for the development and validation of autonomous driving systems. However, existing methods struggle to comprehensively address the autonomy-oriented requirements of balancing: (i) dynamical…

机器人学 · 计算机科学 2026-02-23 Tanmay Vilas Samak , Chinmay Vilas Samak , Bing Li , Venkat Krovi

With the broader adoption and highly successful development of Large Language Models (LLMs), there has been growing interest and demand for applying LLMs to autonomous driving technology. Driven by their natural language understanding and…

Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving,…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Yang Zhou , Hao Shao , Letian Wang , Zhuofan Zong , Hongsheng Li , Steven L. Waslander

Large language models (LLMs) have brought exciting new advances to mobile UI agents, a long-standing research field that aims to complete arbitrary natural language tasks through mobile UI interactions. However, existing UI agents usually…

Simulation-based testing is crucial for validating autonomous vehicles (AVs), yet existing scenario generation methods either overfit to common driving patterns or operate in an offline, non-interactive manner that fails to expose rare,…

人工智能 · 计算机科学 2025-07-16 Yuewen Mei , Tong Nie , Jian Sun , Ye Tian

Autonomous driving training requires a diverse range of datasets encompassing various traffic conditions, weather scenarios, and road types. Traditional data augmentation methods often struggle to generate datasets that represent rare…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Yongjie Fu , Yunlong Li , Xuan Di

Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that such generated data lacks diversity. In this paper, we propose…

计算与语言 · 计算机科学 2026-04-29 Avinash Amballa , Yashas Malur Saidutta , Chi-Heng Lin , Vivek Kulkarni , Srinivas Chappidi

Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Woongyeong Yeo , Kangsan Kim , Jaehong Yoon , Sung Ju Hwang

Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a novel framework that…

计算机视觉与模式识别 · 计算机科学 2025-08-13 Noor Ahmed , Cameron Braunstein , Steffen Eger , Eddy Ilg

Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to rare events.…

Leveraging advanced reasoning capabilities and extensive world knowledge of large language models (LLMs) to construct generative agents for solving complex real-world problems is a major trend. However, LLMs inherently lack embodiment as…

Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering their use in editing scenes and training embodied AI agents. We…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Sicheng Mo , Ziyang Leng , Leon Liu , Weizhen Wang , Honglin He , Bolei Zhou

Autonomous driving systems depend on on models that can reason about high-level scene contexts and accurately predict the dynamics of their surrounding environment. Vision- Language Models (VLMs) have recently emerged as promising tools for…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Stefan Englmeier , Katharina Winter , Fabian B. Flohr

Recent advancements in language-grounded autonomous driving have been significantly promoted by the sophisticated cognition and reasoning capabilities of large language models (LLMs). However, current LLM-based approaches encounter critical…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Ruifei Zhang , Wei Zhang , Xiao Tan , Sibei Yang , Xiang Wan , Xiaonan Luo , Guanbin Li

Recent advancements in foundation models (FMs) have unlocked new prospects in autonomous driving, yet the experimental settings of these studies are preliminary, over-simplified, and fail to capture the complexity of real-world driving…

计算机视觉与模式识别 · 计算机科学 2024-10-16 Yidong Huang , Jacob Sansom , Ziqiao Ma , Felix Gervits , Joyce Chai

This paper introduces TRAILDREAMS, a framework that uses a large language model (LLM) to automate the production of movie trailers. The purpose of LLM is to select key visual sequences and impactful dialogues, and to help TRAILDREAMS to…

多媒体 · 计算机科学 2026-02-04 Roberto Balestri , Pasquale Cascarano , Mirko Degli Esposti , Guglielmo Pescatore

Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among these, motion control - specifying object dynamics and camera trajectories - is essential for…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Muhammed Burak Kizil , Enes Sanli , Niloy J. Mitra , Erkut Erdem , Aykut Erdem , Duygu Ceylan

Autonomous driving technology, a catalyst for revolutionizing transportation and urban mobility, has the tend to transition from rule-based systems to data-driven strategies. Traditional module-based systems are constrained by cumulative…

人工智能 · 计算机科学 2024-08-13 Zhenjie Yang , Xiaosong Jia , Hongyang Li , Junchi Yan