arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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 6450 信号源:cs.AI, cs.LG, cs.CV, cs.RO, cs.MA

1. 通用世界模型 4308 篇

2011.09004 2020-11-19 cs.LG cs.AI cs.HC cs.NE cs.RO 78%

Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data

Aastha Acharya, Rebecca Russell, Nisar R. Ahmed

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based RL(abstract);分类 cs.AI、cs.LG、cs.RO

Comments Accepted to the Workshop on Challenges of Real-World RL at NeurIPS 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.05555 2026-06-05 cs.LG cs.AI 76%

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

表示学习实现可扩展的多任务深度强化学习

Johan Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon, Aaron Courville, Pablo Samuel Castro

机构 * Mila – Québec AI Institute(魁北克AI研究所) Université de Montréal(蒙特利尔大学) McGill University(麦吉尔大学) CIFAR AI Chair(CIFAR人工智能 chair) Google DeepMind(谷歌DeepMind)

专题命中 通用世界模型 :world-model(abstract);world-model(abstract);model-based RL(abstract);分类 cs.AI、cs.LG

AI总结 本文提出一种结合预测性表示学习与高容量值函数近似的无模型算法MR.Q,在无需规划的情况下,在多任务连续控制任务中超越基于世界模型的方法和多种深度强化学习基线,并显著降低计算开销。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08230 2026-04-16 cs.AI 76%

Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions

赋能增益与因果模型构建:儿童和成人对干预可控性和变异性敏感

Eunice Yiu, Kelsey Allen, Shiry Ginosar, Alison Gopnik

机构 * Department of Psychology, University of California, Berkeley(加州大学伯克利分校心理学系) Department of Computer Science, University of British Columbia(不列颠哥伦比亚大学计算机科学系) Toyota Technological Institute at Chicago(芝加哥丰田技术研究所)

专题命中 通用世界模型 :world model(abstract,comments);world model(abstract,comments);world models(comments);分类 cs.AI

AI总结 研究探讨了赋能增益在因果学习中的作用,通过实验验证儿童和成人如何利用赋能信号推断因果关系并设计干预措施。

Comments Accepted to Philosophical Transactions A, Special issue: World models, AGI, and the hard problems of life-mind continuity. Expected publication in 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.13537 2025-11-18 cs.LG cs.AI 76%

Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)

Rodolfo Valiente, Praveen K. Pilly

机构 * Intelligent Systems Center, HRL Laboratories(智能系统中心,HRL实验室)

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI、cs.LG

Comments Replaced all references to "self-awareness" with the more accurate term "self-assessment"; Updated Figure 2; Added recent pertinent work from the cognitive computational neuroscience literature; Removed the non-apples-to-apples comparison with Dreamer-v3 for self-assessment; Added additional experiments to validate the role of accurate self-assessment in effective self-regulation

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21782 2025-06-30 cs.LG cs.RO 76%

M3PO: Massively Multi-Task Model-Based Policy Optimization

Aditya Narendra, Dmitry Makarov, Aleksandr Panov

机构 * Centre for Cognitive Modelling, Moscow Institute of Physics and Technology(认知建模中心,莫斯科物理技术学院) AIRI, the Artificial Intelligence Research Institute(人工智能研究所)

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.LG、cs.RO

Comments 6 pages, 4 figures. Accepted at IEEE/RSJ IROS 2025. Full version, including appendix and implementation details

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17103 2025-06-23 cs.LG cs.AI 76%

TransDreamerV3: Implanting Transformer In DreamerV3

Shruti Sadanand Dongare, Amun Kharel, Jonathan Samuel, Xiaona Zhou

专题命中 通用世界模型 :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
2505.19867 2025-05-27 cs.LG cs.AI 76%

Deep Active Inference Agents for Delayed and Long-Horizon Environments

Yavar Taheri Yeganeh, Mohsen Jafari, Andrea Matta

机构 * Politecnico di Milano(米兰理工学院) Rutgers University(罗切斯特大学)

专题命中 通用世界模型 :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
2405.15616 2024-05-27 cs.AI cs.LG cs.NE 76%

Neuromorphic dreaming: A pathway to efficient learning in artificial agents

Ingo Blakowski, Dmitrii Zendrikov, Cristiano Capone, Giacomo Indiveri

专题命中 通用世界模型 :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
2306.15934 2023-06-29 cs.LG cs.AI stat.ML 76%

Curious Replay for Model-based Adaptation

Isaac Kauvar, Chris Doyle, Linqi Zhou, Nick Haber

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI、cs.LG

Comments Accepted at ICML 2023. Website at https://sites.google.com/view/curious-replay

详情

展开后加载摘要…

URL PDF HTML 收藏
2304.06281 2023-04-14 cs.LG cs.AI cs.MA cs.RO 76%

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

Wenli Xiao, Yiwei Lyu, John Dolan

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO;dynamics model(abstract)

Comments Accepted in AAMAS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2107.08325 2021-07-20 cs.RO cs.AI cs.SY eess.SY 76%

Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning

Peide Cai, Hengli Wang, Huaiyang Huang, Yuxuan Liu, Ming Liu

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based RL(abstract);分类 cs.AI、cs.RO

Comments 8 pages, 8 figures. IEEE Robotics and Automation Letters (RA-L) & IROS 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.01620 2021-05-06 cs.LG cs.AI 76%

Data-Efficient Reinforcement Learning for Malaria Control

Lixin Zou, Long Xia, Linfang Hou, Xiangyu Zhao, Dawei Yin

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI、cs.LG

Comments 7 pages, 4 figures, IJCAI 2021 Accepted Paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.10706 2026-07-07 cs.LG cs.AI 76%

Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling

提升图域外泛化水平:超越显式环境建模的不变学习

Xu Shen, Yixin Liu, Yili Wang, Rui Miao, Yiwei Dai, Shirui Pan, Yi Chang, Xin Wang

机构 * The School of Artificial Intelligence, Jilin University(吉林大学人工智能学院) The School of Information and Communication Technology, Griffith University(格里菲斯大学信息与通信技术学院)

专题命中 通用世界模型 :environment model(title,abstract);分类 cs.AI、cs.LG

AI总结 本文提出MPHIL方法,通过超球面不变表示提取和多原型分类解决图学习中域外泛化问题,提升模型鲁棒性和分类性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.09080 2023-08-21 cs.CV cs.RO 76%

Pedestrian Environment Model for Automated Driving

Adrian Holzbock, Alexander Tsaregorodtsev, Vasileios Belagiannis

专题命中 通用世界模型 :environment model(title,abstract);分类 cs.CV、cs.RO

Comments Accepted for presentation at the 26th IEEE International Conference on Intelligent Transportation Systems (ITSC 2023), 24-28 September 2023, Bilbao, Bizkaia, Spain

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.11708 2022-06-24 cs.LG cs.AI 76%

Reinforcement Learning under Partial Observability Guided by Learned Environment Models

Edi Muskardin, Martin Tappler, Bernhard K. Aichernig, Ingo Pill

专题命中 通用世界模型 :environment model(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.10232 2026-08-12 cs.RO cs.AI cs.LG 新提交 75%

FACT: Failure-Aware Causal Training for World-Action Models

FACT:面向世界-动作模型的故障感知因果训练方法

Quanquan Peng, Yutong Liang, Rui Yan, Nicklas Hansen, Xiaolong Wang

机构 * University of California San Diego(加州大学圣迭戈分校)

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO;dynamics model(abstract)

AI总结 FACT是一种故障感知因果世界-动作模型,通过将错误动作转化为训练目标,在模拟与真实双臂操作任务中提升了世界-动作模型的性能,减少了成功偏差导致的未来幻觉。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.21644 2026-08-05 cs.LG cs.SY eess.SY 版本更新 75%

Toward Goal-Agnostic Joint-Embedding Predictive Control of Partial Differential Equations

迈向偏微分方程的目标无关联合嵌入预测控制

Jonathan Gallagher, Roberto Guglielmi

机构 * University of Waterloo(滑铁卢大学)

专题命中 通用世界模型 :world model(abstract);world model(abstract);latent dynamics(abstract);分类 cs.LG

AI总结 该研究针对偏微分方程提出目标无关控制框架,基于联合嵌入预测架构,通过离线训练小型二维ViT编码器等,经模型预测路径积分控制器复用。在相关基准测试中,KE探测器规划提升奖励、降低误差,验证了潜在动力学与目标无关及校准可观测量用于状态控制的优势。

Comments Associated code will be open sourced alongside a later, updated submission

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.23991 2026-06-24 cs.AI cs.LG cs.MA cs.RO 新提交 75%

Critique of Agent Model

智能体模型批判

Eric Xing, Mingkai Deng, Jinyu Hou

机构 * Institute of Foundation Models, Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学基础模型研究所) School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院)

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.RO

AI总结 本文区分了自动化与智能体,提出真正智能体需内化目标、身份、决策、自我调节和学习等结构,并设计了GIC通用智能体架构。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20583 2026-06-23 cs.NI cs.AI 新提交 75%

Physical-AI: From Channel Awareness to Environmental Intelligence in 6G Wireless Networks

Physical-AI: 从信道感知到6G无线网络中的环境智能

Farooque Hassan Kumbhar, Kapal Dev, Sunder Ali Khowaja, Alexandros-Apostolos A. Boulogeorgos, Mehdi Bennis, Yuanwei Liu

机构 * Augmented Cognition Meta-communications ERC Research Center, Korea University, Korea(增强认知元通信ERC研究中心,韩国大学,韩国) Department of Computer Science, Munster Technological University (MTU)(计算机科学系,穆斯特技术大学(MTU)) School of Computing, Faculty of Engineering and Computing, Dublin City University, Ireland(计算学院,工程与计算学院,都柏林城市大学,爱尔兰) Department of Electrical and Computer Engineering of the Democritus University, Greece(德米特里大学电气与计算机工程系,希腊) Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong(电气与计算机工程系,香港大学,香港) Department of Electronic Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, South Korea(电子工程系, Kyung Hee大学, Yongin-si, Gyeonggi-do 17104, 韩国)

专题命中 通用世界模型 :world model(abstract);world model(abstract);environment model(abstract);分类 cs.AI

AI总结 提出Physical-AI架构,利用自监督时空无线电基础模型将分布式观测转化为共享环境表征,通过多推理头估计阻塞、用户分布等环境属性,并基于神经决策层实现主动控制,降低中断概率和阻塞响应延迟。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.21363 2026-02-24 cs.RO 75%

Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control

迈向大规模预训练与高效微调之间的人形机器人控制的桥梁

Weidong Huang, Zhehan Li, Hangxin Liu, Biao Hou, Yao Su, Jingwen Zhang

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI) School of Artificial Intelligence, Xidian University(人工智能学院,西安电子科技大学)

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based RL(abstract);分类 cs.RO

AI总结 本文提出了一种结合大规模预训练与高效微调的方法,利用SAC实现人形机器人零样本部署,并通过基于模型的方法提升适应效率。

Comments ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12091 2026-01-22 cs.LG 75%

GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes

GraphPerf-RT: 一种基于图的性能模型用于OpenMP代码的硬件感知调度

Mohammad Pivezhandi, Mahdi Banisharif, Saeed Bakhshan, Abusayeed Saifullah, Ali Jannesari

机构 * Wayne State University(韦恩州立大学) Iowa State University(爱荷华州立大学) The University of Texas at Dallas(德克萨斯大学达拉斯分校)

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based RL(abstract);分类 cs.LG

AI总结 GraphPerf-RT通过结合任务拓扑、代码语义和运行时上下文,实现高效硬件感知调度,提升性能与能效。

Comments 49 pages, 4 figures, 19 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01878 2025-12-02 cs.AI 75%

Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoning

图距离作为惊喜:知识图谱推理中的自由能最小化

Gaganpreet Jhajj, Fuhua Lin

机构 * School of Computing(计算学院) Information Systems(信息系统) Athabasca University(亚伯达大学)

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI

AI总结 本文提出利用图距离最小化惊喜来改进知识图谱推理,通过连接自由能原理与KG系统,探索图距离在生成模型中的应用及其对语法结构的影响。

Comments Accepted to NORA Workshop at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.13163 2025-05-13 cs.IR cs.AI 75%

ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

Yi Zhang, Ruihong Qiu, Jiajun Liu, Sen Wang

机构 * The University of Queensland(昆士兰大学) CSIRO DATA61

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based RL(abstract);分类 cs.AI

Comments CIKM 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.09817 2025-03-14 cs.LG cs.AI stat.ML 75%

Temporal Difference Flows

Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Rémi Munos, Alessandro Lazaric, Ahmed Touati

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG;predictive model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.19639 2025-01-19 cs.MA 75%

RMIO: A Model-Based MARL Framework for Scenarios with Observation Loss in Some Agents

Zifeng Shi, Meiqin Liu, Senlin Zhang, Ronghao Zheng, Shanling Dong

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.MA

Comments 17 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.23277 2024-11-04 cs.CV cs.AI cs.CL cs.LG cs.RO 75%

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

Yining Hong, Beide Liu, Maxine Wu, Yuanhao Zhai, Kai-Wei Chang, Linjie Li, Kevin Lin, Chung-Ching Lin, Jianfeng Wang, Zhengyuan Yang, Yingnian Wu, Lijuan Wang

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.08172 2024-10-11 cs.RO cs.AI cs.CV cs.LG 75%

On the Evaluation of Generative Robotic Simulations

Feng Chen, Botian Xu, Pu Hua, Peiqi Duan, Yanchao Yang, Yi Ma, Huazhe Xu

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.CV

Comments Project website: https://sites.google.com/view/evaltasks

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.08691 2024-06-14 cs.CV cs.AI cs.LG cs.RO 75%

UnO: Unsupervised Occupancy Fields for Perception and Forecasting

Ben Agro, Quinlan Sykora, Sergio Casas, Thomas Gilles, Raquel Urtasun

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.16815 2024-02-27 physics.soc-ph cs.AI nlin.AO 75%

Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studies

Bing Yuan, Zhang Jiang, Aobo Lyu, Jiayun Wu, Zhipeng Wang, Mingzhe Yang, Kaiwei Liu, Muyun Mou, Peng Cui

专题命中 通用世界模型 :world model(abstract);world model(abstract);model-based reinforcement learning(abstract);分类 cs.AI

Comments 57 pages, 17 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.15391 2024-02-26 cs.LG cs.AI cs.CV 75%

Genie: Generative Interactive Environments

Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Bechtle, Feryal Behbahani, Stephanie Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang, Konrad Zolna, Jeff Clune, Nando de Freitas, Satinder Singh, Tim Rocktäschel

专题命中 通用世界模型 :world model(abstract);world model(abstract);分类 cs.AI、cs.LG、cs.CV;dynamics model(abstract)

Comments https://sites.google.com/corp/view/genie-2024/

详情

展开后加载摘要…

URL PDF HTML 收藏