世界模型 - arXivDaily 专题

1510.02173 2015-10-12 cs.AI cs.CV cs.LG stat.ML 64%

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

John-Alexander M. Assael, Niklas Wahlström, Thomas B. Schön, Marc Peter Deisenroth

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

1312.0790 2014-03-17 cs.AI cs.LG stat.ML 64%

Test Set Selection using Active Information Acquisition for Predictive Models

Sneha Chaudhari, Pankaj Dayama, Vinayaka Pandit, Indrajit Bhattacharya

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

Comments The paper has been withdrawn by the authors. The current version is incomplete and the work is still on going. The algorithm gives poor results for a particular setting and we are working on it. However, we are not planning to submit a revision of the paper. This work is going to take some time and we want to withdraw the current version since it is not in a good shape and needs a lot more work to be in publishable condition

2602.09572 2026-07-27 cs.DB cs.AI cs.LG 版本更新 62%

Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases

预测查询语言：一种用于关系数据库预测建模的领域特定语言

Vid Kocijan, Jinu Sunil, Jan Eric Lenssen, Viman Deb, Xinwei Xe, Federico Reyes Gomez, Matthias Fey, Jure Leskovec

机构 * Kumo.ai, Stanford University（Kumo.ai，斯坦福大学）

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

AI总结 PQL是一种用于关系数据库预测建模的声明式语言，通过单个查询自动计算训练标签，支持多种机器学习任务，已在金融欺诈、推荐系统等领域应用。

Comments Presented at TaDA@VLDB2026

Journal ref TaDA@VLDB2026

2507.04050 2025-07-08 cs.LG cs.AI 62%

Predictive Modeling of Effluent Temperature in SAT Systems Using Ambient Meteorological Data: Implications for Infiltration Management

Roy Elkayam

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

2410.03736 2024-11-26 cs.HC cs.AI cs.LG 62%

CliMB: An AI-enabled Partner for Clinical Predictive Modeling

Evgeny Saveliev, Tim Schubert, Thomas Pouplin, Vasilis Kosmoliaptsis, Mihaela van der Schaar

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

Comments * Evgeny Saveliev and Tim Schubert contributed equally to this work

2402.01077 2024-08-14 cs.LG cs.AI 62%

Recent Advances in Predictive Modeling with Electronic Health Records

Jiaqi Wang, Junyu Luo, Muchao Ye, Xiaochen Wang, Yuan Zhong, Aofei Chang, Guanjie Huang, Ziyi Yin, Cao Xiao, Jimeng Sun, Fenglong Ma

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

Comments This paper has been accepted by IJCAI 24 Survey Track

2407.06682 2024-07-10 cs.LG cs.AI 62%

A Predictive Model Based on Transformer with Statistical Feature Embedding in Manufacturing Sensor Dataset

Gyeong Taek Lee, Oh-Ran Kwon

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

2405.03943 2024-05-08 cs.LG cs.AI 62%

Predictive Modeling with Temporal Graphical Representation on Electronic Health Records

Jiayuan Chen, Changchang Yin, Yuanlong Wang, Ping Zhang

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

Comments IJCAI 2024 main track

2307.13865 2023-09-20 cs.CV cs.LG 62%

Pretrained Deep 2.5D Models for Efficient Predictive Modeling from Retinal OCT

Taha Emre, Marzieh Oghbaie, Arunava Chakravarty, Antoine Rivail, Sophie Riedl, Julia Mai, Hendrik P. N. Scholl, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Ursula Schmidt-Erfurth, Hrvoje Bogunović

专题命中通用世界模型：predictive model(title,abstract)；分类 cs.LG、cs.CV；predictive models(abstract)

Comments Accepted at OMIA-X MICCAI'23 Workshop

2212.10839 2023-07-31 cs.LG cs.AI cs.DB stat.ML 62%

Consistent Range Approximation for Fair Predictive Modeling

Jiongli Zhu, Sainyam Galhotra, Nazanin Sabri, Babak Salimi

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

2208.14582 2023-06-26 cs.LG cs.AI cs.CY 62%

A Prescriptive Learning Analytics Framework: Beyond Predictive Modelling and onto Explainable AI with Prescriptive Analytics and ChatGPT

Teo Susnjak

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

Comments revision of the original paper to include ChatGPT integration

Journal ref 2023

2306.00040 2023-06-02 cs.LG cs.AI cs.NE 62%

Assessing the Generalizability of a Performance Predictive Model

Ana Nikolikj, Gjorgjina Cenikj, Gordana Ispirova, Diederick Vermetten, Ryan Dieter Lang, Andries Petrus Engelbrecht, Carola Doerr, Peter Korošec, Tome Eftimov

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

Comments To appear at GECCO 2023

2304.04566 2023-04-11 cs.LG cs.AI stat.ME 62%

Linking a predictive model to causal effect estimation

Jiuyong Li, Lin Liu, Ziqi Xu, Ha Xuan Tran, Thuc Duy Le, Jixue Liu

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

Comments 16

1608.05745 2017-02-28 cs.LG cs.AI cs.NE 62%

RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism

Edward Choi, Mohammad Taha Bahadori, Joshua A. Kulas, Andy Schuetz, Walter F. Stewart, Jimeng Sun

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

Comments Accepted at Neural Information Processing Systems (NIPS) 2016

2608.10790 2026-08-12 cs.CV cs.AI 新提交 60%

MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams

MVTrack：基于压缩比特流的超高速无外观运动目标跟踪器

Iñaki Erregue, Kamal Nasrollahi, Sergio Escalera

机构 * Universitat de Barcelona（巴塞罗那大学）； Computer Vision Center（计算机视觉中心）； Aalborg Universitet（奥尔堡大学）； Milestone Systems（里程碑系统公司）

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

AI总结针对RGB目标检测器计算成本高的问题，提出直接基于H.264比特流的MVTrack，结合MVDet与MVLink，在VIRAT上性能优于YOLO26n且参数量、FLOPs、延迟大幅降低，可实现高效监控跟踪。

Comments This paper has been accepted to the 2nd workshop on Low-Level Vision Frontiers with Generative AI, Preference Optimization, Agentic Systems and World Models (LoViF) at ECCV2026

2608.00632 2026-08-04 cs.LG stat.ML 新提交 60%

Learning the Pareto Frontier of Predictive Models under Distribution Shift

分布偏移下预测模型帕累托前沿的学习

Yiming Dong, Jiwei Zhao, Yang Young Lu

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校）

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.LG

AI总结本研究提出Frontier Learning框架，将预训练模型库视为互补信息源，通过拼接白盒内部表示与黑盒预测输出构建特征，在分布偏移场景中提升预测性能，表现优于或相当于最强的单个复用策略。

Comments 28 pages, 4 figures, 3 tables

2607.24569 2026-07-28 physics.flu-dyn cs.LG 新提交 60%

The balance between compactness and forecast accuracy of data-driven latent-space reduced-order models in controlled wake flows

数据驱动的潜在空间降阶模型在受控尾流中的紧凑性与预测精度平衡

Alberto Solera-Rico, Patricia García-Caspueñas, Carlos Sanmiguel Vila, Stefano Discetti

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

AI总结研究受控尾流中数据驱动潜在空间降阶模型，比较POD、CAEs等压缩方法及基于长短期记忆网络的预测器，发现CAEs压缩效率高但长期预测差，POD潜在轨迹更平滑，揭示紧凑性与预测精度权衡，为实时流动控制设计预测ROMs提供指导。

Comments 32 pages, 20 figures

2511.10687 2026-07-03 cs.MA cs.AI cs.CL cs.GT 版本更新 60%

Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents

谁获得奖励 & 谁受到责备？面向多LLM智能体的评估对齐训练信号

Chih-Hsuan, Yang, Tanwi Mallick, Le Chen, Krishnan Raghavan, Amal Gueroudji, Ian T. Foster, Rajeev Thakur

机构 * Argonne National Laboratory（阿贡国家实验室）； University of Chicago（芝加哥大学）

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

AI总结提出一个理论框架，结合合作博弈归因与过程奖励建模，将系统级评估转化为智能体信用和消息级信号，用于多LLM智能体训练。

Comments Accepted at the NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (LAW 2025)

1502.02251 2026-06-04 stat.ML cs.LG cs.RO cs.SY eess.SY 60%

From Pixels to Torques: Policy Learning with Deep Dynamical Models

从像素到扭矩：基于深度动态模型的策略学习

Niklas Wahlström, Thomas B. Schön, Marc Peter Deisenroth

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

AI总结本文提出一种高效的数据驱动强化学习算法，通过深度动态模型直接从像素信息学习闭环控制策略，解决高维观测下的连续状态-动作空间数据高效学习问题。

Comments 9 pages

2605.16205 2026-05-18 cs.AI cs.CL cs.LG cs.MA cs.SY eess.SY 60%

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

上下文、推理与层次：在对抗性POMDP中的复合LLM代理设计成本-性能研究

Igor Bogdanov, Chung-Horng Lung, Thomas Kunz, Jie Gao, Adrian Taylor, Marzia Zaman

机构 * Carleton University（卡尔顿大学）

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

AI总结研究探讨了在对抗性部分可观测序贯环境中，复合LLM代理设计的上下文、推理和层次分解对性能与成本的影响，发现程序化状态抽象在成本效率上表现最佳，而分层分解无需推理可获得最佳性能。

2605.08958 2026-05-12 cs.LG 60%

Learning predictive models for combinations of heterogeneous proteomic data sources

学习异质蛋白质组数据源的预测模型

Michal Valko, Richard Pelikan, Miloš Hauskrecht

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.LG

AI总结本文研究了两种蛋白质混合物表达数据源的个体和联合效用，提出了一种模型融合方法以最大化异质数据集的结合效益。

Comments Published at in AMIA Summit on Translational Bioinformatics (STB 2008

2512.02228 2025-12-03 cs.AI cs.LG 60%

STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls

STRIDE：一种选择AI模态的系统框架——代理AI、AI助手或LLM调用

Shubhi Asthana, Bing Zhang, Chad DeLuca, Ruchi Mahindru, Hima Patel

机构 * IBM Research – Almaden（IBM阿尔马登研究实验室）； IBM Research – Yorktown（IBM约克镇研究实验室）； IBM Research – India（IBM印度研究实验室）

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

AI总结 STRIDE提供了一种系统框架，帮助选择AI模态，通过评估任务动态性决定是否使用自主代理，提升效率并降低成本。

Comments 10 pages, 4 Figures, 5 Tables Paper presented at NeurIPS 2025 LAW workshop: Bridging Language, Agent, and World Models

2402.13928 2025-10-16 math.OC 60%

Partial State-Feedback Reduced-Order Switching Predictive Models for Next-Generation Optical Lithography Systems

Raaja Ganapathy Subramanian, Barry Moest, Bart Paarhuis

专题命中通用世界模型：predictive model(title,abstract)；predictive models(title)

Comments Preprint accepted for CEP-Elsevier

2505.04886 2025-05-13 cs.HC cs.LG 60%

Fairness Perceptions in Regression-based Predictive Models

Mukund Telukunta, Venkata Sriram Siddhardh Nadendla, Morgan Stuart, Casey Canfield

机构 * Missouri University of Science and Technology（密苏里科技大学）； United Network for Organ Sharing（器官共享联合网络）

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.LG

2405.05572 2025-05-06 cs.CL cs.AI 60%

From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences

Prashant Kodali, Anmol Goel, Likhith Asapu, Vamshi Krishna Bonagiri, Anirudh Govil, Monojit Choudhury, Ponnurangam Kumaraguru, Manish Shrivastava

机构 * IIIT Hyderabad（IIIT海得拉尔）； Technical University of Darmstadt（达姆施塔特技术大学）； MBZUAI ； Microsoft（微软）

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.AI

2503.22068 2025-03-31 cs.LG cs.AI 60%

A Proposal for Networks Capable of Continual Learning

Zeki Doruk Erden, Boi Faltings

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

Comments Published at ICLR 2025 World Models Workshop

2503.15516 2025-03-21 cs.HC cs.AI 60%

In Pursuit of Predictive Models of Human Preferences Toward AI Teammates

Ho Chit Siu, Jaime D. Peña, Yutai Zhou, Ross E. Allen

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.AI

2503.09719 2025-03-14 cs.LG 60%

Towards Causal Model-Based Policy Optimization

Alberto Caron, Vasilios Mavroudis, Chris Hicks

专题命中通用世界模型：model-based reinforcement learning(abstract)；分类 cs.LG；predictive model(abstract)；predictive models(abstract)

2411.03224 2024-11-06 cs.LG 60%

Interpretable Predictive Models for Healthcare via Rational Logistic Regression

Thiti Suttaket, L Vivek Harsha Vardhan, Stanley Kok

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.LG

Comments ICIS 2021 Proceedings ( see https://aisel.aisnet.org/icis2021/is_health/is_health/18 )

2410.00946 2024-10-08 eess.IV cs.LG 60%

Spectral Graph Sample Weighting for Interpretable Sub-cohort Analysis in Predictive Models for Neuroimaging

Magdalini Paschali, Yu Hang Jiang, Spencer Siegel, Camila Gonzalez, Kilian M. Pohl, Akshay Chaudhari, Qingyu Zhao

专题命中通用世界模型：predictive model(title)；predictive models(title)；分类 cs.LG

1. 通用世界模型 4314 篇

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

Test Set Selection using Active Information Acquisition for Predictive Models

Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases

Predictive Modeling of Effluent Temperature in SAT Systems Using Ambient Meteorological Data: Implications for Infiltration Management

CliMB: An AI-enabled Partner for Clinical Predictive Modeling

Recent Advances in Predictive Modeling with Electronic Health Records

A Predictive Model Based on Transformer with Statistical Feature Embedding in Manufacturing Sensor Dataset

Predictive Modeling with Temporal Graphical Representation on Electronic Health Records

Pretrained Deep 2.5D Models for Efficient Predictive Modeling from Retinal OCT

Consistent Range Approximation for Fair Predictive Modeling

A Prescriptive Learning Analytics Framework: Beyond Predictive Modelling and onto Explainable AI with Prescriptive Analytics and ChatGPT

Assessing the Generalizability of a Performance Predictive Model

Linking a predictive model to causal effect estimation

RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism

MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams

Learning the Pareto Frontier of Predictive Models under Distribution Shift

The balance between compactness and forecast accuracy of data-driven latent-space reduced-order models in controlled wake flows

Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents

From Pixels to Torques: Policy Learning with Deep Dynamical Models

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

Learning predictive models for combinations of heterogeneous proteomic data sources

STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls

Partial State-Feedback Reduced-Order Switching Predictive Models for Next-Generation Optical Lithography Systems

Fairness Perceptions in Regression-based Predictive Models

From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences

A Proposal for Networks Capable of Continual Learning

In Pursuit of Predictive Models of Human Preferences Toward AI Teammates

Towards Causal Model-Based Policy Optimization

Interpretable Predictive Models for Healthcare via Rational Logistic Regression

Spectral Graph Sample Weighting for Interpretable Sub-cohort Analysis in Predictive Models for Neuroimaging