State Representation Learning

Ask about this topic

Overview

State representation learning asks how an agent or model can turn observations and histories into an internal state that preserves what matters for future prediction or action. Methods include predictive objectives such as JEPA and successor representations, inverse-dynamics and bisimulation learning, recurrent belief states, and task- or reward-driven abstractions. They are studied in partially observed control, pixel-based robot planning, navigation, and dynamical-system forecasting, where useful states can improve sample efficiency, transfer, and robustness. A central tension is that predictive accuracy or reconstruction does not guarantee a decision-sufficient state: representations must retain control-relevant distinctions without carrying irrelevant detail, and their adequacy remains difficult to measure.

Latest papers

CardsList

126 papers22 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

  1. Probing Spatial State Representations in Visual Foundation Models

    Oct 29, 2026Baiqiao Yin, Zhongang Cai, Ruisi Wang +3Visual Spatial ReasoningVision Foundation Models

    New York University · Nanyang Technological University · The Hong Kong University of Science and Technology +1

  2. SWIM: Learning What Matters from Behaviors for JEPA World Models

    Oct 27, 2026Jiaming Hu, Shi Bo, Yan Zheng +11World Models for RoboticsWorld Model-Based Planning

    Boston University · Unity Technologies

  3. DepState-JEPA: Learning Depth-Grounded State Representation for Visual Perception and Manipulation

    Oct 21, 2026Xiujian Liang, Liuyuan Na, Zehao Du +6State Representation LearningVisual Representation Learning

    Fudan University · Shanghai Innovation Institute (SII) · Shanghai Jiao Tong University +2

  4. Understanding the Inner Workings of a State-Space Foundation Model for Limit Order Books

    Oct 20, 2026Valentin Mohl, Alexandre Bismuth, Aramis Marti-Shahandeh +6Limit Order Book ModelingState Representation Learning

    British Open-ended Learning and Discovery Lab (BOLD), Department of Computer Science, University of Oxford, Oxford, United Kingdom · Harvard University, Cambridge, MA, United States · British Open-ended Learning and Discovery Lab (BOLD), Department of Engineering Science, University of Oxford, Oxford, United Kingdom +3

  5. World Models with Configurable Perception

    Oct 20, 2026Yijun Shen, Delong Chen, Xianming Hu +2World Model LearningWorld Model-Based Planning

    East China Normal University · HKUST

  6. EASformer: Environment-Action-State Alignment for Industrial Generative Ranking

    Oct 20, 2026Bohao Li, DingLun Cao, Pengcheng Huang +11Learning to RankGenerative Recommendation

    Beihang University, Beijing, China · Harbin Institute of Technology, Shenzhen, China · Independent Researcher, Shanghai, China +1

  7. Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments

    Oct 19, 2026Yubo Ye, Sweekar Piya, Xiajun Jiang +1Latent Dynamics ModelingTime Series Forecasting

    Department of Computing and Information Sciences, Rochester Institute of Technology, Rochester, New York, USA · Department of Computer Science, Rowan University, Glassboro, New Jersey, USA

  8. Ontic state recovery through prediction

    Oct 19, 2026Ping Zhang, Quang-Huy Nguyen, Yingtie Lei +1Predictive State RepresentationsState Representation Learning

    Boston University · The Ohio State University

  9. CoRe-WM: Conditioned Response-State World Modeling for Longitudinal Treatment-Response Prediction in Breast DCE-MRI

    Oct 18, 2026Lin Zhao, Bowen Chen, Qiaohui Gao +4Cancer Drug Response PredictionClinical Outcome Prediction

    Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ 07102, USA. · College of Engineering, Northeastern University, Boston, MA 02115, USA. · Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, USA. +2

  10. Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry

    Oct 14, 2026Ren Zhuang, Ben Wang, Shuifa SunRL for Language Model ReasoningPolicy Optimization

    Hangzhou Normal University

  11. PatientWM: Towards Generalizable Clinical World Models via Unified Patient States

    Oct 12, 2026Ziwen Kan, Jie Peng, Bo Yan +5Action-Conditioned World ModelsClinical Prediction

    University of Science and Technology of China · University of Central Florida · Princeton University +2

  12. World Modeling through Spectral Alignment

    Oct 11, 2026Holger Molin, William Peng, Marco Bagatella +1World Model LearningLatent World Models

    Stanford University · Brown University

  13. State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study

    Oct 11, 2026Dong Nie, Rui Lan, Yixin Nie +1LLM AgentsTransfer Learning

    Independent Researcher · University of North Texas

  14. Active Neural Matter: A Finite-Window Response Framework for Physical Systems and Distributed AI Workflows

    Oct 10, 2026Tianchi Chen, Shihua YuState Representation Learning

    Merck & Co., Inc., Rahway, NJ, USA · Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA

  15. Neuromotor Hierarchy Network: Physiological Inductive Biases for Robust Generalization in sEMG Decoding

    Oct 6, 2026He Wang, Hongyuan Qi, Zhaoxian Zhang +4Neural DecodingState Representation Learning

    National University of Singapore

  16. Block Disentanglement in CRL: Bridging Identifiability and Visual State Estimation

    Oct 5, 2026Emre Acartürk, Pranamya Kulkarni, Puranjay Datta +3Causal Representation LearningCausal Identifiability

    Rensselaer Polytechnic Institute Troy, NY, USA · Swiss AI, EPFL Lausanne, Switzerland · University of Delaware Newark, DE, USA

  17. Attention-Based Surface Representation Learning for Robot State Prediction and Open-Ended Surface Classification

    Oct 3, 2026Oleg Kushnarev, Alexander BelyaevRobotic PerceptionClassification

    National Research Tomsk Polytechnic University, Tomsk, 634050 Russia

  18. Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization

    Oct 1, 2026Parthiv Chatterjee, Kashish Kanjaria, Vashisth Purani +2User ModelingState Tracking

    KDM Lab, Dhirubhai Ambani University · Dhirubhai Ambani University · LCS2 Lab, Indian Institute of Technology Delhi

  19. Learning Transferable Skills using Goal-Conditioned Bisimulation

    Sep 30, 2026Mohammad Amin Abbasfar, Farbod Azimmohseni, Mohammad Hossein RohbanAgent Skill LearningTrajectory Representation Learning

    Department of Computer Engineering Sharif University of Technology

  20. Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?

    Sep 30, 2026Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque +2Offline RLRepresentation Learning for RL

    Department of Robotics and Mechatronics Engineering, University of Dhaka, Bangladesh · Department of Computer Science, University of Oxford, UK

  21. Learning Continuous Neural Representation of Stochastic Hybrid Systems

    Sep 30, 2026Sangli Teng, Hang Liu, Koushil SreenathDynamical SystemsStochastic Differential Equations

  22. Learning Macroscopic Dynamics without Reconstructing Microscopic States

    Sep 29, 2026Zhichao Han, Yue Zhao, Qianxiao LiLatent Dynamics ModelingState Representation Learning

    National University of Singapore

  23. Abductive World Modeling via Causal Representation Learning

    Sep 29, 2026Ziqi Liu, Songhan Yang, Linfan Zhou +4Causal Representation LearningAbductive Reasoning

    BAIZ Team

  24. Retracing Hodgkin and Huxley: State Recovery Does Not Certify Mechanism

    Sep 28, 2026Peiyu Zang, Jiayi Hao, Yongqiang CaiDynamical SystemsLatent Dynamics Modeling

    School of Mathematical Sciences, Beijing Normal University

  25. Hamiltonian JEPA: Action-Conditioned World Models with an Inherited Control State

    Sep 27, 2026Tamim Zoabi, Ameen Ali, Lior WolfJoint-Embedding Predictive ArchitectureModel-Based Planning

    The Blavatnik School of Computer Science, Tel Aviv University

  26. Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret

    Sep 26, 2026Bingyu Shen, Boyang LiState TrackingState Representation Learning

    Independent Researcher · Department of Computer Science and Technology Kean University, Union, NJ, USA

  27. Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions

    Sep 26, 2026Mohit Kumar, Somayeh KargaranKoopman Operator LearningState Abstraction

    University of Rostock, Rostock, Germany · Software Competence Center Hagenberg, Hagenberg, Austria

  28. What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response

    Sep 26, 2026Enzo Nicolás Spotorno, Josafat Leal Filho, Antônio Augusto FröhlichLatent Dynamics ModelingState Representation Learning

    Department of Informatics and Statistics Federal University of Santa Catarina

  29. STRIDE: State-Transition Representation via Increment Dynamics and Evolution

    Sep 26, 2026Yuchen Xiong, Siming Huang, Jianfeng SunTime Series ForecastingProbabilistic Time Series Forecasting

  30. Tracking States or Tracking Cosets? An Algebraic Account of Learned State Tracking

    Sep 24, 2026Zhiyu Zhang, Yupeng LiTransformerRecurrent Neural Networks

    Conflux Labs Ltd · Michigan State University