Temporal Representation Learning

Latest papers

28 papers8 papers in the last four weeks, up 60% on the four weeks before. 0.0% of all new papers.

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
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 +3Geospatial Representation Learning 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 +3Video Representation Learning Vision Foundation Models
Lassonde School of Engineering, York University, Toronto, Canada · Vector Institute, Toronto, Canada · FAIR, Meta Superintelligence Labs +2
Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models
Aug 31, 2026Xingyu Ding, Yuzhong Zhao, Chunhai Zhao +3Representation Learning Temporal Representation Learning
Nanjing University, Nanjing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning
Aug 30, 2026Yun Li, Jun Xiao, Cong Zhang +1Temporal Action Segmentation Temporal Representation Learning
School of Control Science and Engineering, Shandong University
Composed Historical Image Retrieval by Modeling Temporal Representations
Aug 19, 2026Adrià Molina Rodríguez, Oriol Ramos Terrades, Josep Lladós CanetTemporal Representation Learning Representation Learning
Centre de Visió per Computador Universitat Autònoma de Barcelona Bellaterra, Catalonia · Computer Science Department Universitat Autònoma de Barcelona, Bellaterra, Catalonia
ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models
Aug 10, 2026Adrien Schoen, Nachiketa Ratnakar Patil, Arjun Bhagoji +1Representation Learning Temporal Representation Learning
Institut universitaire de France
TimePLE: Rethinking Temporal Representation for Video Temporal Grounding
Jul 27, 2026Yuhui Zeng, Xinyu Mao, Xiaokun Liu +4Temporal Video Grounding Representation Learning
Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Kling Team, Kuaishou Technology, China · The Chinese University of Hong Kong, HKSAR, China +1
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
Jun 14, 2026Ninad Daithankar, Alexi Gladstone, Yann LeCun +1Visual Representation Learning Video Representation Learning
1UIUC · 2New York University
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Jun 5, 2026Paarth Gulati, Ilya NemenmanContrastive Learning Representation Learning
Department of Physics, and Initiative in Theory and Modeling of Living Systems, Emory University, Atlanta, GA
Stateful Visual Encoders for Vision-Language Models
Jun 3, 2026Zirui Wang, Junwei Yu, Adam Yala +3Vision-Language Models Visual Representation Learning
1Voio, Inc. · 2UC Berkeley · 3UCSF
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
May 29, 2026Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad +1Multivariate Time Series Forecasting Joint-Embedding Predictive Architecture
C3 AI, Redwood City, CA, USA
STEP: Learning STructured Embeddings for Progressive Time Series
May 29, 2026Lucas Thil, Jesse Read, Rim Kaddah +1Self-Supervised Time Series Representation Learning Interpretable ML
LIX, École Polytechnique IRT SystemX Palaiseau, France · IRT SystemX Palaiseau, France · Safran Tech Chateaufort, France
The TIME Machine: On The Power of Motion for Efficient Perception
May 21, 2026Mantas Skackauskas, Xinyue Hao, Laura Sevilla-LaraRepresentation Learning Video Representation Learning
School of Informatics University of Edinburgh
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
May 21, 2026Zelin Zheng, Xinyan Liu, Ruixin Li +4Temporal Video Grounding Temporal Representation Learning
School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · Beijing Key Laboratory of Embodied Intelligence Computing, Beijing, China · Faculty of Computing, Harbin Institute of Technology, Weihai, China +1
Divide and Contrast: Learning Robust Temporal Features without Augmentation
May 20, 2026Abdul-Kazeem Shamba, Kerstin Bach, Gavin TaylorContrastive Learning Self-Supervised Learning
Department of Computer Science, Norwegian University of Science and Technology, Norway · Department of Computer Science, United States Naval Academy, USA.
Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
May 8, 2026Peitao Han, Fei Cheng, Lis K. Pereira +2Video-Language Models Temporal Reasoning in Language Models
The University of Osaka · Center for Information and Neural Networks · National Institute of Information and Communications Technology +2
Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction
Apr 9, 2026Marco Gabriele Fedozzi, Yukie Nagai, Francesco Rea +1Temporal Representation Learning Robotics
DIBRIS Department, University of Genoa, Via All’Opera Pia 13 16145 Genoa, Italy · CONTACT Unit, Italian Institute of Technology, Via Enrico Melen 83, 16152 Genoa, Italy · International Research Center for Neurointelligence, The University of Tokyo 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033, Japan
It's a Matter of Time: Three Lessons on Long-Term Motion for Perception
Feb 16, 2026Willem Davison, Xinyue Hao, Laura Sevilla-LaraMotion Representation Learning Temporal Video Understanding
University of Edinburgh

Oct 15, 2026J/K move · Enter open · S save

Twice Upon a Time: Complementary Representations for Time-Series Reasoning

Hedi Zisling, Liran Nochumsohn, Ilan Naiman, Mihir Parmar+1

Ben-Gurion University · Google

Time Series Language Modeling Time Series Reasoning Time Series Representation Learning Temporal Representation Learning Multi-View Learning

Open paper AskPDF arXiv

Time Series Language Models (TSLMs) enable language-based understanding and reasoning over temporal data, yet a fundamental question remains: what information should their time-series representations preserve, and what variation should they factor out? Existing TSLMs typically expose the language model to a single representation, imposing a fixed inductive bias across downstream tasks. We instead introduce complementary representations as a design principle for time-series reasoning. Our model combines two visual views: line plots preserve absolute measurements and the observed coordinate frame, while normalized delay embeddings factor out positive amplitude rescaling and offsets while exposing temporal structure. Dedicated visual encoders integrate both views into a shared language model through visual tokens and multi-level feature fusion. Evaluation-time interventions verify that the two views exhibit distinct invariance profiles, while single-view ablations show that their combination is particularly beneficial beyond basic perception, with the large gains in prediction and reasoning. Built on Qwen3-VL-8B, our dual-view model improves overall TSRBench accuracy from 44.5% with line plots alone to 53.2%, substantially exceeding the strongest evaluated dedicated TSLM baseline at 36.7%. It further achieves 89.9% accuracy on TSExam and 86.8% numerical accuracy on multivariate ChatTS alignment. Together, these results demonstrate that complementary representations provide an effective design principle for general-purpose TSLMs, enabling models to exploit temporal structure without sacrificing access to the original measurement frame.