arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

世界模型

面向环境建模、时序预测、仿真规划、具身智能和自动驾驶的世界模型方法与应用。

共收录 320 信号源:cs.AI, cs.LG, cs.CV, cs.RO, cs.MA

1. 仿真与规划 320 篇

2605.14398 2026-06-02 cs.AI 81%

Coding Agent Is Good As World Simulator

编码智能体作为世界模拟器

Hongyu Wang, Jingquan Wang, Bocheng Zou, Radu Serban, Dan Negrut

机构 * Department of Mechanical & Aerospace Engineering, University of Wisconsin-Madison(威斯康星大学麦迪逊分校机械与航空航天工程系) School of Computer, Data, and Information Sciences, University of Wisconsin-Madison(威斯康星大学麦迪逊分校计算机、数据与信息科学学院)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 提出一个通过可执行模拟代码构建基于物理的世界模型的智能体框架,协调规划、代码生成、视觉审查和物理分析智能体,迭代修正代码以满足物理约束,在物理准确性、指令忠实度和视觉质量上超越视频模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17682 2026-05-19 cs.CV 81%

GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning

GEM:用于占用预测和运动规划的高斯演化模型

Cheng Chen, Hao Huang, Saurabh Bagchi

机构 * Purdue University(普渡大学) New York University Abu Dhabi(纽约大学阿布扎克分校)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 该研究提出GEM模型,通过高斯演化模型实现高效的占用预测和运动规划,解决了传统方法在时间灵活性、场景演化和连续时间动态匹配上的不足。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04341 2026-05-04 cs.LG 81%

Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism

长周期基于模型的离线强化学习无需显式保守性

Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon

机构 * Mila - Quebec AI Institute(魁北克人工智能研究所) McGill University(麦吉尔大学)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 本文提出NEUBAY算法,通过贝叶斯方法解决长周期rollout中的价值过估计问题,在D4RL和NeoRL基准上取得新进展。

Comments ICML 2026. 50 pages, 15 figures. Code is available at https://github.com/twni2016/neubay

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.07209 2026-04-14 cs.CV 81%

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

INSPATIO-WORLD:通过时空自回归建模实现实时4D世界模拟器

InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu, Haoyu Ji, Hujun Bao, Hongjia Zhai, Jialin Liu, Jing Guo, Nan Wang, Siji Pan, Weihong Pan, Weijian Xie, Xianbin Liu, Xiaojun Xiang, Xiaoyu Zhang, Xinyu Chen, Yifu Wang, Yipeng Chen, Zhenzhou Fan, Zhewen Le, Zhichao Ye, Ziqiang Zhao

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 本文提出INSPATIO-WORLD框架,通过时空自回归模型实现从单帧视频恢复和生成高保真动态交互场景,解决空间一致性和实时交互难题,实现在WorldScore-Dynamic基准中领先。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.07426 2026-04-10 cs.LG cs.AI 81%

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control

GIRL:通过信息论幻觉控制实现生成性想象强化学习

Prakul Sunil Hiremath

机构 * Department of Computer Science and Engineering, Visvesvaraya Technological University (VTU), Belagavi, India(维斯瓦拉亚科技大学计算机科学与工程系,贝拉加维,印度) Aliens on Earth (AoE) Autonomous Research Group, Belagavi, India(地球外星人自主研究组,贝拉加维,印度)

专题命中 仿真与规划 :world-model(abstract);world-model(abstract);model-based reinforcement learning(abstract);world model(comments)

AI总结 GIRL通过引入跨模态锚定信号和不确定性适应信任区域瓶颈,解决模型误差累积导致的轨迹漂移问题,提升长周期任务的样本效率和回报性能。

Comments 20 pages, 2 figures, 7 tables; reinforcement learning, world models

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.20169 2026-03-23 cs.CV cs.MM 81%

EgoForge: Goal-Directed Egocentric World Simulator

EgoForge:面向目标的自体世界模拟器

Yifan Shen, Jiateng Liu, Xinzhuo Li, Yuanzhe Liu, Bingxuan Li, Houze Yang, Wenqi Jia, Yijiang Li, Tianjiao Yu, James Matthew Rehg, Xu Cao, Ismini Lourentzou

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of California San Diego(加州大学圣地亚哥分校)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 EgoForge通过最小静态输入生成连贯的第一人称视频,结合VideoDiffusionNFT提升意图对齐和时间一致性,实现在动态环境模拟中的优越性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03618 2026-03-10 cs.LG 81%

Open-World Reinforcement Learning over Long Short-Term Imagination

开放世界长期短期想象强化学习

Jiajian Li, Qi Wang, Yunbo Wang, Xin Jin, Yang Li, Wenjun Zeng, Xiaokang Yang

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(人工智能大模型关键实验室、人工智能研究院、上海交通大学) Ningbo Institute of Digital Twin, Eastern Institute of Technology(宁波数字孪生研究院、技术东院) School of Computer Science and Technology, East China Normal University(计算机科学与技术学院、华东师范大学)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 本文提出LS-Imagine方法,通过扩展想象 horizon 提高开放世界强化学习中长期收益的探索效率。

Comments Accepted by ICLR 2025 Oral. Project page: https://qiwang067.github.io/ls-imagine

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.03974 2026-02-05 cs.AI 81%

Active Epistemic Control for Query-Efficient Verified Planning

主动认知控制用于查询高效的验证规划

Shuhui Qu

机构 * Stanford University(斯坦福大学)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

AI总结 主动认知控制通过结合基于模型的信念管理和范畴可行性检查,实现查询高效的验证规划,在交互环境中减少重新规划轮次。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13371 2025-11-18 cs.AI 81%

Cognitive Maps in Language Models: A Mechanistic Analysis of Spatial Planning

Caroline Baumgartner, Eleanor Spens, Neil Burgess, Petru Manescu

机构 * University College London(伦敦大学学院) University of Oxford(牛津大学)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10670 2025-10-14 cs.CV 81%

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes

Yu Li, Menghan Xia, Gongye Liu, Jianhong Bai, Xintao Wang, Conglang Zhang, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Yujiu Yang

机构 * Tsinghua University(清华大学) HUST(华中科技大学) Kling Team, Kuaishou Technology(快手科技 Kling 团队) HKUST(香港科技大学) Zhejiang University(浙江大学) Wuhan University(武汉大学)

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18507 2025-08-27 cs.AI 81%

Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies

Dillon Z. Chen, Johannes Zenn, Tristan Cinquin, Sheila A. McIlraith

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

Comments RLC 2025 Workshop on Programmatic Reinforcement Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.02938 2022-08-08 cs.AI cs.PL 81%

Abstract Interpretation for Generalized Heuristic Search in Model-Based Planning

Tan Zhi-Xuan, Joshua B. Tenenbaum, Vikash K. Mansinghka

专题命中 仿真与规划 :world model(abstract);world models(abstract);world model(abstract);world models(abstract)

Comments 4 pages, 2 figures. Presented at the ICML 2022 Workshop on Beyond Bayes: Paths Towards Universal Reasoning Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.04568 2026-08-07 cs.LG cs.AI cs.RO 版本更新 78%

Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination

Dream-MPC:基于梯度与潜在想象的模型预测控制

Jonathan Spieler, Sven Behnke

机构 * Autonomous Intelligent Systems, Computer Science Institute VI - Intelligent Systems(自主智能系统,计算机科学研究所VI - 智能系统) Robotics, Center for Robotics(机器人学,机器人中心) the Lamarr Institute for Machine Learning(拉马尔机器学习研究所) Artificial Intelligence, University of Bonn, Germany(人工智能,波恩大学,德国)

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI、cs.LG、cs.RO

AI总结 提出Dream-MPC方法,通过从展开策略生成少量候选轨迹,并利用学习的世界模型进行梯度上升优化,结合不确定性正则化和时间上的优化迭代摊销,显著提升了底层策略性能,在24个连续控制任务上优于无梯度MPC和现有基线。

Comments Accepted for International Conference on Machine Learning (ICML) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.14418 2026-06-15 cs.AI cs.LG cs.RO 新提交 78%

Causal Object-Centric Models for Planning with Monte Carlo Tree Search

用于蒙特卡洛树搜索规划的因果对象中心模型

Rodion Vakhitov, Leonid Ugadiarov, Alexey Skrynnik, Aleksandr Panov

机构 * MIRAI CogAILab

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI、cs.LG、cs.RO

AI总结 提出COMET算法,结合无监督对象中心编码器和Transformer世界模型,通过动作-槽融合机制和对象因果注意力实现高效规划,在多个基准上优于基线方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16030 2026-05-28 cs.LG cs.RO 76%

Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds

Mind Dreamer: 通过潜在流形上的主动因果干预释放想象力

Shaojun Xu, Xiaoling Zhou, Yihan Lin, Yapeng Meng, Xinglong Ji, Luping Shi, Rong Zhao

机构 * Center for Brain-Inspired Computing Research, Department of Precision Instrument, Tsinghua University, Beijing, China(脑启发计算研究中心,精密仪器系,清华大学,北京,中国) College of Computer Science and Technology, Zhejiang University, Hangzhou, China(计算机科学与技术学院,浙江大学,杭州,中国) Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen, China(彭途萨微纳米科学与技术研究院,厦门大学,厦门,中国)

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.LG、cs.RO

AI总结 针对基于模型的强化学习中历史束缚导致策略优化滞后的问题,提出Mind Dreamer框架,通过主动因果干预生成非连续潜在跳跃,并推导中继价值函数与中继不确定性函数,实现样本效率提升。

Comments 34 pages, 7 figures, ICML 2026 accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.05011 2025-10-21 cs.AI cs.CV 76%

DARIL: When Imitation Learning outperforms Reinforcement Learning in Surgical Action Planning

Maxence Boels, Harry Robertshaw, Thomas C Booth, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin

机构 * Surgical and Interventional Engineering, King's College London, London, UK(外科与介入工程,伦敦国王学院,伦敦,英国) Interventional Engineering, King's College London, London, UK(介入工程,伦敦国王学院,伦敦,英国)

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based RL(abstract);分类 cs.AI、cs.CV

Comments Paper accepted at the MICCAI2025 workshop proceedings on COLlaborative Intelligence and Autonomy in Image-guided Surgery (COLAS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.15283 2024-02-26 cs.LG cs.AI 76%

When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination

Martin Benfeghoul, Umais Zahid, Qinghai Guo, Zafeirios Fountas

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17058 2026-05-19 cs.LG 75%

Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning

学习多时间尺度抽象以进行分层组合规划

Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen

机构 * Department of Electrical Engineering(电气工程系) Automation, Aalto University, Finland(自动化,艾尔沃斯大学,芬兰)

专题命中 仿真与规划 :world model(abstract);world model(abstract);latent dynamics(abstract);分类 cs.LG

AI总结 本文提出了一种基于模型的分层框架,用于解决序列随机组合决策问题,通过多时间尺度目标结构化潜在动态,实现高效的前瞻规划,并联合学习子目标条件预算策略以支持上下文感知的资源分配。

Comments 34 pages, 8 figures, 23 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16787 2025-12-19 cs.AI 75%

Enter the Void - Planning to Seek Entropy When Reward is Scarce

进入虚无 - 在奖励稀缺时规划以寻求熵

Ashish Sundar, Chunbo Luo, Xiaoyang Wang

机构 * Department of Computer Science University of Exeter(计算机科学系埃克塞特大学)

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI

AI总结 本文提出了一种基于世界模型的分层规划方法,在奖励稀缺时主动寻找信息丰富的状态,提升样本效率,应用于Dreamer时在迷宫任务中效率提升50%。

Comments 10 pages without appendix, 15 Figures, preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09985 2025-06-12 cs.AI cs.CV cs.LG cs.RO 75%

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Mido Assran, Adrien Bardes, David Fan, Quentin Garrido, Russell Howes, Mojtaba, Komeili, Matthew Muckley, Ammar Rizvi, Claire Roberts, Koustuv Sinha, Artem Zholus, Sergio Arnaud, Abha Gejji, Ada Martin, Francois Robert Hogan, Daniel Dugas, Piotr Bojanowski, Vasil Khalidov, Patrick Labatut, Francisco Massa, Marc Szafraniec, Kapil Krishnakumar, Yong Li, Xiaodong Ma, Sarath Chandar, Franziska Meier, Yann LeCun, Michael Rabbat, Nicolas Ballas

机构 * FAIR at Meta Mila -- Quebec AI Institute

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.CV

Comments 48 pages, 19 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2010.12142 2020-10-26 cs.LG 75%

Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning

Guangxiang Zhu, Minghao Zhang, Honglak Lee, Chongjie Zhang

专题命中 仿真与规划 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.LG

Comments Published on 34th Conference on Neural Information Processing Systems (NeurIPS 2020)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22138 2026-05-22 cs.AI cs.CL cs.LG cs.RO 73%

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

通过自我调节模拟规划实现高效的代理推理

Mingkai Deng, Jinyu Hou, Lara Sá Neves, Varad Pimpalkhute, Taylor W. Killian, Zhengzhong Liu, Eric P. Xing

机构 * Institute of Foundation Models (IFM)(基础模型研究所) Carnegie Mellon University(卡内基梅隆大学)

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO

AI总结 本文提出通过分解决策过程为三个系统:模拟推理、自我调节和反应执行,来提升代理推理的效率,并展示了SR$^2$AM模型在不同任务中的表现。

Comments Code and model artifacts are available at https://github.com/sailing-lab/sr2am

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16848 2026-05-19 cs.CV cs.AI cs.CL cs.LG 73%

Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction

基于模式的思考:通过模式诱导突破视觉规划中的感知瓶颈

Yichang Jian, Boyuan Xiao, Zhenyuan Huang, Yifei Peng, Yao-Xiang Ding

机构 * State Key Lab of CAD& CG(CAD与CG国家重点实验室)

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.CV

AI总结 本文提出通过模式诱导的方法,利用模式推理和模式诱导策略,使视觉语言模型在视觉规划任务中实现更高效和准确的感知与推理,解决传统模型在复杂输入下的感知瓶颈问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.06861 2025-05-28 cs.RO cs.AI cs.CV 73%

Efficient Robotic Policy Learning via Latent Space Backward Planning

Dongxiu Liu, Haoyi Niu, Zhihao Wang, Jinliang Zheng, Yinan Zheng, Zhonghong Ou, Jianming Hu, Jianxiong Li, Xianyuan Zhan

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.CV、cs.RO

Comments Accepted by ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.10196 2024-09-17 cs.RO cs.AI cs.CV 73%

NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions

Zhixi Cai, Cristian Rojas Cardenas, Kevin Leo, Chenyuan Zhang, Kal Backman, Hanbing Li, Boying Li, Mahsa Ghorbanali, Stavya Datta, Lizhen Qu, Julian Gutierrez Santiago, Alexey Ignatiev, Yuan-Fang Li, Mor Vered, Peter J Stuckey, Maria Garcia de la Banda, Hamid Rezatofighi

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.CV、cs.RO

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.06673 2023-11-14 cs.LG cs.AI cs.RO 73%

Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination

Lu Wen, Songan Zhang, H. Eric Tseng, Huei Peng

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.04114 2022-06-10 cs.AI cs.LG cs.RO stat.ML 73%

Deep Hierarchical Planning from Pixels

Danijar Hafner, Kuang-Huei Lee, Ian Fischer, Pieter Abbeel

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO

Comments Website: https://danijar.com/director

详情

展开后加载摘要…

URL PDF HTML 收藏
2011.13897 2021-05-04 cs.LG cs.AI cs.RO stat.ML 73%

Latent Skill Planning for Exploration and Transfer

Kevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO

Comments First two authors contributed equally. Published as a conference paper in ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2102.09812 2021-02-22 cs.LG cs.AI cs.RO 73%

Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space

Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Lucas Liebenwein, Ryan Sander, Sertac Karaman, Daniela Rus

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO

Comments Wilko, Tim, and Igor contributed equally to this work; published in Conference on Robot Learning 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.24720 2026-07-28 cs.CL cs.AI cs.LG 新提交 71%

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

多轮长期规划的物理学:通过单教师和多教师策略蒸馏从预训练到训练后

Tianyi Men, Zhuoran Jin, Kang Liu, Jun Zhao

机构 * Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) University of Chinese Academy of Sciences(中国科学院大学)

专题命中 仿真与规划 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG

AI总结 研究多轮长期规划问题,通过引入统一可控环境,利用预训练、GRPO、OPD及MOPD等方法,研究规划能力在不同阶段的获取、塑造与整合,展示了多教师策略蒸馏对跨环境能力整合的作用。

详情

展开后加载摘要…

URL PDF HTML 收藏