Predictive Representation Learning

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 156% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 116

All topics

MiniWAM: Learning Compact Future Targets for Efficient World-Action Modeling
Oct 8, 2026Jie Chen, Ruofei Bai, Yuxin Cai +5World Models for Robotics World Action Models
Department of Mechanical Engineering, National University of Singapore, Singapore · A*STAR Institute of Advanced Intelligence and Computing (A*STAR IAIC), Singapore · Nanyang Technological University, Singapore
PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary
Oct 8, 2026Chenyang Xu, Donglin Xie, Xi Xiang +12Predictive Representation Learning Representation Learning
OPPO Health Lab, Guangdong OPPO Mobile Telecommunications Corp., Ltd. · Xidian University · Peking University +3
Intervention anchors and scientific verification in synthetic vascular predictive representations
Oct 8, 2026Lingsen You, Yujun Guo, Xinyu Zhong +4Representation Identifiability Predictive Representation Learning
Department of Cardiology, Zhongshan Hospital, Fudan University, Shanghai Institute of Cardiovascular Diseases, State Key Laboratory of Cardiovascular Diseases, NHC Key Laboratory of Ischemic Heart Diseases, National Clinical Research Center for Interventional Medicine, Key Laboratory of Viral Heart Diseases, Chinese Academy of Medical Sciences, Shanghai 200032, China. · Institutes of Biomedical Sciences, Fudan University, Shanghai 200030, China. · College of Biomedical Engineering, Fudan University, Shanghai 200438, China. +1
PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving
Oct 8, 2026Jinchang Xu, Hongda Yu, Fengwei Dong +9End-to-End Autonomous Driving World Model-Based Planning
Southeast University · NIO · Nanyang Technological University +1
Patient, Place, Prior (P $^3$ ): What Counts as Personalization in Medical World Models?
Oct 6, 2026Xingrui Gu, Hanxue Gu, Yuxiang Zhang +1Longitudinal Medical Image Analysis Predictive Representation Learning
University of California, Berkeley · University of California, San Francisco · Southern Methodist University
Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations
Oct 6, 2026K. P. Santoso, N. Z. Fadil, F. P. Harsanti +2Non-Autoregressive Text Generation Predictive Representation Learning
School of Computing, National University of Singapore · Department of Information Technology, Institut Teknologi Sepuluh Nopember · Avalon AI +1
EMG-GPT: Predictive Pretraining on Residual-Quantized EMG Tokens for Hand Pose Estimation
Oct 4, 2026Ettore Magni, Rolandos Alexandros Potamias, Stefanos Zafeiriou +1Representation Learning Self-Supervised Time Series Representation Learning
Imperial College London
Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry
Oct 1, 2026Xinjian Zhao, Yaoyao Xu, Xuemin Chen +2Molecular Optimization Joint-Embedding Predictive Architecture
School of Data Science, The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory
Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
Oct 1, 2026Efstathios Karypidis, Spyros Gidaris, Nikos KomodakisVideo Prediction Predictive Representation Learning
Archimedes, Athena Research Center, Greece · National Technical University of Athens · University of Crete +1
World-as-Graph: Relational World Modeling Through Latent Space Graphs
Sep 30, 2026Yaqi Yang, Shuo Huang, Yujin Huang +3Graph Structure Learning World Model Learning
School of Computing Technologies, RMIT University, Australia · Faculty of Information Technology, Monash University, Australia · KStelrix Star Dynamics Lab, KStelrix, China +1
PrecipJEPA: JEPA-Regularized Future-State Prediction with Motion-Source Rendering for Precipitation Nowcasting
Sep 30, 2026Yufeng Zhu, Dan Niu, Qiliang Wu +4Precipitation Forecasting Joint-Embedding Predictive Architecture
Department of Automation, Southeast University, Nanjing 210096, China
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
Sep 29, 2026Gaspard Botté, Séverin Baroudi, Samir Sadok +5Joint-Embedding Predictive Architecture Predictive Representation Learning
Concordia University · Mila – Qu´ebec AI Institute · Univ Toulon, Aix Marseille Univ, CNRS, LIS +4
Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
Sep 29, 2026Fabian A. Mikulasch, Friedemann ZenkeLatent Variable Models Representation Identifiability
Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland · Faculty of Science, University of Basel, Switzerland
Learning Expressive and Compositional Motion Representation via Spectral Skills
Sep 29, 2026Feiyang Wu, Chenxiao Gao, Chen Yang +3Robot Skill Learning Humanoid Robot Control
Georgia Institute of Technology
Anisotropic Representations Improve Planning in JEPA World Models
Sep 29, 2026Mingu Kang, Yoori Oh, Sookyung Kim +1Representation Learning World Model-Based Planning
Seoul National University · Ewha Womans University
Where Predictive Supervision Goes Shapes What VLA Policies Learn
Sep 29, 2026Hanseul Kim, Jewon Yeom, Youngjoon Jeong +2Visuomotor Policy Learning Vision-Language-Action Models
Graduate School of Data Science Seoul National University
Generative Residual Factorization
Sep 28, 2026Letian Gong, Yuzhou HongRepresentation Collapse Latent Variable Models
Zhejiang University of Science and Technology · Zhejiang Sci-Tech University
PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
Sep 28, 2026Zhentao Tan, Jianrong Zhang, Ruijie Quan +1Latent Dynamics Modeling Joint-Embedding Predictive Architecture
Zhejiang University.
DisKO: Deep Koopman Learning in Distribution Space from Unpaired Snapshots
Sep 28, 2026He Ma, Xiaochen Liu, Wanfeng Lu +3Koopman Operator Learning Latent Dynamics Modeling
School of Mathematical Sciences, Fudan University, China. · Research Institute of Intelligent Complex Systems, Fudan University, China. · Shanghai Center for Mathematical Sciences, Fudan University, China. +2
Shaping Persistent Representations from Independent Interactions
Sep 28, 2026Ji Dai, Quan Fang, Junyu Gao +4Representation Learning Latent Dynamics Modeling
Beijing University of Posts and Telecommunications · Institute of Automation, Chinese Academy of Sciences · Shenzhen University +1
Conditional Predictive Sufficient Statistics for Visual Representation Learning
Sep 25, 2026Yuzhou HongVisual Representation Learning Predictive Representation Learning
Zhejiang Sci-Tech University
A JEPA Recipe for Tabular Foundation Models
Sep 22, 2026Mingyu Jeon, Suwan Cho, Jae Young SuhTabular Foundation Models Self-Supervised Pre-Training
Modulabs, Seoul, Republic of Korea
Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors
Sep 21, 2026Elizaveta Kovtun, Matvey Konovalov, Andrey Sakhovskiy +1Tactile Sensing Self-Supervised Learning
Sber AI, Moscow, Russia · Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · HSE University, Moscow, Russia +1
JEPA-Anything: Learning Predictive Models across Different Worlds
Sep 17, 2026Taoyong Cui, Zhongyao Wang, Xinyue Xu +10World Model Learning Joint-Embedding Predictive Architecture
Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates
Sep 17, 2026Yuhei Fujioka, Daitaro Misawa, Shingo FukumaRepresentation Learning Hierarchical Representation Learning
Cancerscan Inc., Tokyo, Japan · Kyoto University, Graduate School of Medicine, Kyoto, Japan · Hiroshima University, Graduate School of Biomedical and Health Sciences, Hiroshima, Japan
RAF-VLA: Representation Alignment with the Future for End-to-End Autonomous Driving
Sep 15, 2026Dogun Kim, Yongjae Lee, Joonhee Lim +4End-to-End Autonomous Driving Vision-Language-Action Models
Graduate School of Mobility, Korea Advanced Institute of Science & Technology (KAIST), Daejeon, Korea · Robotics Program, Korea Advanced Institute of Science & Technology (KAIST), Daejeon, Korea
SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning
Sep 15, 2026Rajiv Ranjan, Udaiveer Singh, Shashank Tamaskar +1Multivariate Time Series Forecasting Geospatial Foundation Models
Plaksha University Mohali, Punjab, India · Purdue University West Lafayette, Indiana, USA
World Models for Cross-Machine CNC Transfer under Partial Sensor Overlap
Sep 13, 2026Ayoub Louaye Bouaziz, Matthieu Ostertag, Anton DemaslesManufacturing World Model Learning
Université de Bretagne Occidentale, Brest, France · Mines Nancy, Université de Lorraine, Nancy, France
JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction
Sep 9, 2026Jie Xu, Kangjin Yu, Ziyi Jin +5Joint-Embedding Predictive Architecture Visuomotor Policy Learning
Anyverse Dynamics
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection
Sep 1, 2026Guanzhong Sun, Junyi Ma, Yuxuan Wu +2Cross-Subject EEG Decoding Self-Supervised Pre-Training
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China · School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China +1

Oct 8, 2026, cs.ROJ/K move · Enter open · S save

MiniWAM: Learning Compact Future Targets for Efficient World-Action Modeling

Jie Chen, Ruofei Bai, Yuxin Cai, Yifeng Zhang+4

Department of Mechanical Engineering, National University of Singapore, Singapore · A*STAR Institute of Advanced Intelligence and Computing (A*STAR IAIC), Singapore · Nanyang Technological University, Singapore

World Models for Robotics World Action Models Predictive Representation Learning

Open paper AskPDF arXiv

World modeling has emerged as an effective co-training objective for robot policies, giving rise to World Action Models (WAMs) that jointly predict actions and future states. However, most WAMs predict future states in the native representation space of pretrained visual backbones, resulting in high-dimensional targets with substantial training cost. We introduce MiniWAM, which instead predicts compact future representations learned from privileged current-future transitions. To construct these targets, we propose Predictive Representations via Inverse Spatiotemporal Modeling (PRISM), which combines inverse-dynamics supervision with feature reconstruction to emphasize control-relevant transition information while preserving useful future-state information. With the learned PRISM encoder frozen, MiniWAM is trained to jointly predict the resulting targets and robot actions from current observations. With 65

\times

fewer native future feature tokens, MiniWAM consistently outperforms native future-feature prediction with both DINOv3 and WAN2.1 VAE features, while achieving up to an 8

\times

speedup in world-action training. At 0.25B parameters, MiniWAM is already competitive with substantially larger WAMs on LIBERO, LIBERO-Plus, and RoboTwin 2.0 simulation benchmarks. Representation analyses further show that PRISM contributes behavioral structure beyond feature reconstruction alone. These results demonstrate that effective world-action modeling does not require predicting native visual futures, and that compact predictive representations provide a strong and substantially more efficient target for policy learning. The project page is available at: https://j1dan.github.io/MiniWAM.

Momentum

Related topics

Latest papers 116