Temporal Representation Learning

Latest papers

47 papers16 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Invariance before structure: two modes of emergent compression in representation learning
Nov 5, 2026Hardik Rajpal, Dan GoodmanInvariant Representation Learning Temporal Representation Learning
I-X Centre for AI in Science, Department of Electrical and Electronics Engineering, Imperial College London, London, UK, SW7 2AZ
TAPES: Task-Aligned Joint Predictive Pretraining for Transaction Event Sequences
Nov 3, 2026Ruobing Zuo, Weiyu Han, Huilin He +6Predictive Representation Learning Temporal Representation Learning
East China Normal University · Ant International · Tongji University
E2I-Flow: EEG-to-Image Reconstruction via Wavelet-Temporal Cross-Attention and Conditional Flow Matching
Nov 3, 2026Haowei Pan, Hwa Hui Tew, Junn Yong Loo +3EEG-to-Image Reconstruction EEG-Based Visual Decoding
School of Information Technology, Monash University, Malaysia Campus · School of Electrical and Electronic Engineering, Nanyang Technological University · Statistics Program, King Abdullah University of Science and Technology
Clocks all the way down: does sequence-processing AI need endogenous temporal structure?
Nov 3, 2026Meysam Hashemi, Alireza Valizadeh, Viktor JirsaTemporal Representation Learning Neural Encoding
Institut de Neurosciences des Systèmes, Aix Marseille Université, INSERM, Marseille, 13005, France. · Zapata Briceño Institute for Human Intelligence Research, Madrid, Spain.
Factorized Representations of Concurrent Temporal Variables in Pretrained Language Models
Oct 29, 2026Xinhe Zhang, Arnau Marin-LlobetRepresentation Geometry in Language Models Temporal Representation Learning
Learning Scientific Trajectories to Predict Future Biomedical Discoveries
Oct 28, 2026Chia-Hsuan Chang, Brian Ondov, Jiang Lv +7Scientific Hypothesis Generation AI-Assisted Scientific Research
Department of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT 06510, USA · Department of Cell Biology, Yale School of Medicine, New Haven, CT 06520, USA · Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea +1
Evaluating AlphaEarth Embeddings for Crop Classification: Separability, Temporal Dynamics, and Cross-Regional Transferability
Oct 27, 2026Priyanka Goyal, Maitreyee Sar, Adway Mitra +1Crop Type Classification Agricultural Image Analysis
Department of Artificial Intelligence, Indian Institute of Technology Kharagpur, West Bengal, India · Centre for Atmospheric Sciences, Indian Institute of Technology Delhi, India · Tata Consultancy Services Research, Kolkata, India
Exploring perceptual straightness in learned visual representations
Oct 26, 2026Anne Harrington, Vasha DuTell, Ayush Tewari +4Visual Representation Learning Temporal Representation Learning
MIT CSAIL · MIT Brain and Cognitive Sciences · Woven Planet
AudioFM: Towards General Purpose Audio Representation Learning
Oct 25, 2026Yamin Li, Ruidong Zhang, Anran Wang +19Audio Representation Learning Temporal Representation Learning
Google Research · Vanderbilt University · Google DeepMind +1
Organizing Temporal Evidence in Hyperbolic Space for Video Moment Retrieval
Oct 23, 2026Mengnan Liu, Sanping Zhou, Kun Xia +3Video Moment Retrieval Temporal Video Grounding
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China. · School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China. · Amazon Alexa AI, Bellevue, WA 98004 USA.
OlmoEarth v1.3: Embeddings
Oct 23, 2026Gabriel Tseng, Favyen Bastani, Patrick Alan Johnson +13Geospatial Representation Learning Multimodal Embedding
Allen Institute for AI
Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling
Oct 22, 2026Yifeng Yao, Jinghan Li, Zhihao Zhang +5Video Representation Learning Self-Supervised Visual Representation Learning
Peking University · ByteDance · UNC-Chapel Hill
Slot-JEPA: Object-Structured Prediction Interfaces for Latent World Models
Oct 20, 2026Peisong Wen, Qianqian Xu, Minye Lei +3Goal-Conditioned Planning Joint-Embedding Predictive Architecture
School of Computer Science and Technology, University of Chinese Academy of Sciences · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence +2
Global Time-Aware Conditioning (GTC): A Mechanism for Time-Aware Pediatric Sleep Representation Learning
Oct 19, 2026Saurav Raj Pandey, Harlin LeeTemporal Representation Learning Self-Supervised Time Series Representation Learning
Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA · School of Data and Information Sciences, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
TimesJev: Thinking Fast on Time Series with System 1 Sufficiency
Oct 19, 2026Chenghao Liu, Wei Fan, Jindong Han +4Time Series Reasoning Temporal Representation Learning
University of Auckland · Shandong University · Northeast Normal University +2
ChronoChart: Setup-Agnostic Channel Charting for Label-Free Indoor Localization
Oct 18, 2026Majid Sharghi Foroushani, Jonas Pirkl, Jonathan Ott +4Wireless Localization Temporal Representation Learning
Fraunhofer Institute for Integrated Circuits (IIS), Division Positioning and Networks, 90411 Nürnberg, Germany · Programming Systems Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91052 Erlangen, Germany · Machine Learning and Positioning Systems Lab, University of Technology Nuremberg (UTN), Nürnberg, Germany
HiPPO Functional Memory: Coordinate-Queryable Attention for Irregular Time Series
Oct 17, 2026Zhaodong Guo, Haoyun FengIrregular Time-Series Modeling Sequence Modeling
Imperial College London
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
Oct 15, 2026Hedi Zisling, Liran Nochumsohn, Ilan Naiman +2Time Series Language Modeling Time Series Reasoning
Ben-Gurion University · Google
Local Temporal Contrasts on Human Motion Data Induce a Latent Geometry
Oct 15, 2026Lourenço A. Rodrigues, Felix PutzeTemporal Representation Learning Self-Supervised Time Series Representation Learning
Cognitive Systems Lab FB3, Department of Mathematics and Computer Science, University of Bremen Bremen, 28359 Bremen, Germany
Time-JEPA: Grounding Video World Models with Physical Time Series
Oct 14, 2026Shenyi Li, Ziyang Zhang, Wen Wu +2Video World Models Physical Reasoning in Video
Harbin Institute of Technology · Shanghai Artificial Intelligence Laboratory · Tsinghua University
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
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
Oct 1, 2026Youngwoo Shin, Yusung Ro, Minseo Kim +1Video-Language Models Activation Steering
Korea Advanced Institute of Science and Technology (KAIST)
ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning
Sep 28, 2026Nico Bohlinger, Jan PetersRL for Robotics Representation Learning
Technical University of Darmstadt, Germany · Robotics Institute Germany (RIG); German Research Center for AI (DFKI); hessian.AI
W2Rep: Learning Visual Representations by Watching the World Change
Sep 28, 2026Wen Huang, Hang Guo, Jiarui Yang +3Video Representation Learning Self-Supervised Visual Representation Learning
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Nankai University, Tianjin, China · Shenzhen University, Shenzhen, China
Progressive Memory Transformer: Memory-Aware Attention for Time-Series
Sep 25, 2026Tord Sture Stangeland, Andreas Köhler, Steffen Mæland +1Self-Supervised Time Series Representation Learning Temporal Representation Learning
University of Oslo, Department of Informatics, Oslo, Norway · NORSAR, Lillestrøm, Norway · University of Tromsø, Department of Geosciences, Tromsø, Norway +1
TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval
Sep 23, 2026Mourad Hassani, Julien Romero, Amel Bouzeghoub +1Sentence Embeddings Temporal IR
SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, France · Aldebaran Care, France
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Sep 20, 2026Markus Karmann, Shile Li, Christian Internò +10Joint-Embedding Predictive Architecture Latent World Models
University of Oxford · vivo Tech Research GmbH · Bielefeld University +5
Chronosphere: Space-Time Tessellation of Local Climate Experts
Sep 18, 2026Daniel Cher, Eric Xing, Kexing Li +3Spatiotemporal Representation Learning Geospatial Representation Learning
Washington University in St. Louis · Taylor Geospatial Institute
The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
Sep 3, 2026Yumeng Shi, Quanyu Long, Yin Wu +1Video-Language Models Video Representation Learning
Nanyang Technological University
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
Sep 1, 2026Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3Physical Reasoning in Video Vision Foundation Models
Lassonde School of Engineering, York University, Toronto, Canada · Vector Institute, Toronto, Canada · FAIR, Meta Superintelligence Labs +2

Nov 5, 2026J/K move · Enter open · S save

Invariance before structure: two modes of emergent compression in representation learning

Hardik Rajpal, Dan Goodman

I-X Centre for AI in Science, Department of Electrical and Electronics Engineering, Imperial College London, London, UK, SW7 2AZ

Invariant Representation Learning Temporal Representation Learning Embedding Compression

Open paper AskPDF arXiv

Learned representations show striking invariance across biological and artificial neural networks, with different substrates and variations driven by drift, heterogeneity and initialisation. To understand this invariance, we propose Emergent Adaptive Representation Learning (EARL), a framework that distinguishes two modes of emergence in learned representations: state-space compression, where a learned representation gains predictive power over its own future beyond what the network's units can predict individually, and parameter-space compression, where networks with different micro-level parameters converge to the same representation. We formalise both as Fisher sensitivities and introduce ensemble-level information-theoretic measures for each. In a recurrent reservoir with a trained bottleneck, parameter-space compression rises within the first few epochs of training and partly independently of the task, whereas state-space compression rises about 30 epochs later and only when the network begins to learn the temporal structure of the task. These results suggest that invariance to the substrate and task-specific emergent structure are acquired in distinct phases of learning.