Chronos

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 39

All topics

ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning
Sep 28, 2026Nico Bohlinger, Jan PetersGoal-Conditioned Reinforcement Learning Offline Reinforcement Learning
Technical University of Darmstadt, Germany · Robotics Institute Germany (RIG); German Research Center for AI (DFKI); hessian.AI
Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels
Sep 16, 2026Souhardya Chattopadhyay, Julian Oelhaf, Antonia Schoening +5Accurate Short-Term Electricity Load Forecasting Chronos
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg · Siemens AG, Smart Infrastructure · Department of Electrical Engineering, Media and Computer Science, Ostbayerische Technische Hochschule Amberg-Weiden
ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models
Aug 10, 2026Adrien Schoen, Nachiketa Ratnakar Patil, Arjun Bhagoji +1Dual-Branch Temporal Modeling Autoregressive Model
Institut universitaire de France
ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models
Aug 10, 2026Sam Siavoshian, Omar Ramadan, Amir K. Saeed +3Chronos Frozen Language Model
Independent Researcher, California, USA · Johns Hopkins University, Whiting School of Engineering, Baltimore, MD, USA
FedChronos: Federated Fine-Tuning of Time-Series Foundation Models for Privacy-Preserving Commodity Price Forecasting
Aug 2, 2026Amit Sharma, Nitin Auluck, Akramul AzimTime Series Foundation Models Wireless Foundation Models
Indian Institute of Technology Ropar, Punjab, India · Ontario Tech University, Oshawa, Canada
ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent Memory
Jul 30, 2026Yongye Su, Wujiang Xu, Chaoji Zuo +1Rollback Long-Term Memory
Purdue University · USA · Rutgers University
ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling
Jul 29, 2026Yiwen Chen, Joshua Ainslie, Krzysztof Choromanski +4Rotary Position Embedding Sequence Modeling
YouTube · Google DeepMind
Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models
Jul 22, 2026Luukas Peräkylä, Fahad Sohrab, Ville Hautamäki +3Time Series Foundation Models Heart Rate
Tampere University, Tampere, Finland · University of Eastern Finland, Finland
The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI
Jul 20, 2026Om Narayan, Ramkinker Singh, Praveen BaskarRealistic Threat Model LLM Defense Mechanisms
Department of Computer Science New York University New York, NY, USA · Carnegie Mellon University Pittsburgh, PA, USA · Independent Researcher Chicago, IL, USA
Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation
Jul 17, 2026Muntaser Syed, Marius Silaghi, Sheikh Abujar +1Chronos Inference-Time
Florida Institute of Technology · University of Alabama at Birmingham · Daffodil International University
GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing
Jul 17, 2026Yujie Li, Jiancheng Pan, Zhiwei Wei +3Remote Sensing Land Cover
Beijing University of Posts and Telecommunications Haidian, Beijing, China · Tsinghua University Haidian, Beijing, China · Hunan Normal University Changsha, Hunan, China +1
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
Jul 13, 2026Huan ZhuInduction Reasoning Skills
Peking University
Autoregressive latent diffusion for 3D molecule generation
Jul 10, 2026Federico Ottomano, Gaopeng Ren, Yingzhen Li +2Molecular Generation Autoregressive Diffusion
Department of Chemistry Imperial College London · Department of Computing Imperial College London
Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics
Jul 2, 2026Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber +5Accurate Short-Term Electricity Load Forecasting Time Series Foundation Models
Karlsruhe Institute of Technology (KIT), Germany and Netze BW GmbH, Germany · Netze BW GmbH, Germany · Karlsruhe Institute of Technology (KIT), Germany
Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation
Jun 29, 2026Yulin Zhou, Yimeng Wang, Nengyu Wang +9Long-Horizon Manipulation Robot Policies
School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization
Jun 19, 2026Jiaming He, Jiashu Zhang, Guanyu Hou +4Text-To-Video Generation Model Denoising Trajectory
Nanyang Technological University · Jilin University · The University of Manchester
ChronoSurv: A Clinical Pathway-Guided Graph Framework for Multimodal Survival Analysis
Jun 17, 2026Hugo Miccinilli, Theo Di PiazzaSurvival Predictions Patient Trajectories
Université Paris-Saclay, CentraleSupélec, MICS, France · University of Lyon, INSA Lyon, CREATIS, France
Chronological Blindness: Benchmarking Temporal Reasoning in Vision-Language Models with CHRONOSIGHT
Jun 15, 2026Parthaw Goswami, Jaynto Goswami DeepTemporal Reasoning Recent Vision-Language Models
Department of Computer Science, University of Missouri, Columbia, 65201, MO, USA · SAP, Prague, Czech Republic
ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation
Jun 12, 2026Dongdong Nian, Dongqi Fu, Chenliang Xu +4Recommendation Chronos
University of Rochester · Meta MRS · MBZUAI
Vector Space of Cycles
Jun 6, 2026Moo K. Chung, Anass B. El-Yaagoubi, Hernando OmbaoRecurrence Statistical Inference
Department of Biostatistics and Medical Informatics, University of Wisconsin, Madison, Wisconsin, USA · Statistics Program, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?
Jun 6, 2026Bin Zhu, Yanhao Jia, Kexin Zhao +12Multimodal Reasoning Multimodal Large Language Models
Peking University, Shenzhen Graduate School · 2Peng Cheng Laboratory · Rabbitpre Intelligence +3
ChronosAD: Leveraging Time Series Foundation Models for Accurate Anomaly Detection
May 31, 2026Uzair Khan, Luigi Capogrosso, Francesco Biondani +4Time-Series Anomaly Detection Time Series Foundation Models
University of Verona · Interdisciplinary Transformation University of Austria · ETH Zurich
CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces
May 22, 2026Joydeep ChandraTemporal Knowledge Graphs Matching Markets
BNRIST, Tsinghua University Beijing, China
CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
May 22, 2026León Begiristain, Olaf Dünkel, Adam KortylewskiWorld Models Chronos
University of Freiburg · Freiburg im Breisgau, Germany · Max Planck Institute for Informatics +3
Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues
May 21, 2026Chaogui GouCounseling Conversational Datasets
University of Science and Technology Beijing
Empirical evaluation of Time Series Foundation Models for Day-ahead and Imbalance Electricity Price Forecasting in Belgium
May 16, 2026Chi Bui, Maria Margarida Mascarenhas, Arnaud Verstraeten +1Electricity Price Forecasting Time Series Foundation Models
ELECTA-ESAT (KU Leuven) Leuven, Belgium · ELECTA-ESAT(KU Leuven) and Gridual Leuven, Belgium
In-Context Learning for Data-Driven Censored Inventory Control
May 14, 2026Sohom Mukherjee, Anh-Duy Pham, Richard Pibernik +1Inventory Control Adaptive Sampling
Julius-Maximilians-Universität Würzburg · National University of Singapore Zaragoza Logistics Center
Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
May 12, 2026Gaspard Berthelier, Mariia Baranova, Andrei-Tiberiu Pantea +4Time Series Foundation Models Covariate Balancing
EDF R&D, Palaiseau · Inria Sophia-Antipolis, Université Côte d’Azur · Université Paris Cit'e
ChronoSC: Task-Oriented Semantic Communication via Temporal-to-Color Encoding
May 11, 2026Phuc H. Nguyen, Trung T. Nguyen, Quy N. Duong +1Video Compression Semantic Communications
Smart Green Transformation Center (GREEN-X), VinUniversity, Vietnam. · School of Computer Science and Statistics, Trinity College Dublin, Ireland
Coarsening Linear Non-Gaussian Causal Models with Cycles
May 11, 2026Francisco Madaleno, Francisco C Pereira, Alex MarkhamCausal Modeling Causal Representation Learning
Department of Technology, Management and Economics, Technical University of Denmark · Department of Mathematical Sciences,11 University of Copenhagen
TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
May 11, 2026Hangchen Liu, Dongyuan Li, Renhe Jiang +3Inference-Time Artificial Intelligence Agents
The University of Tokyo · Southern University of Science and Technology
Preliminary Insights in Chronos Frequency Data Understanding and Reconstruction
May 7, 2026Alessandro Pagani, Marco Cominelli, Liying Han +11Time Series Foundation Models Frequency Domain
DII, University of Brescia, Italy. · DEIB, Politecnico di Milano, Italy. · ECE Department, University of California, Los Angeles, USA. +6
Stable Blanket with Hidden Variables and Cycles
May 3, 2026Hanqing XiangCausal Graph Markov
Department of Mathematics, KTH Royal Institute of Technology, Sweden · University of Copenhagen
HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval
Apr 20, 2026Zixu Li, Yupeng Hu, Zhiwei Chen +4Composed Image Retrieval Multimodal Retrieval
School of Software, Shandong University
Chronax: A Jax Library for Forecasting and Conformal Inference
Apr 17, 2026Xan Carey, Arsh Singh, Yash Deshmukh +8Time Series Forecasting Chronos
Simulacrum New York City, NY, USA
Chronos: The AI Co-Historian
Apr 4, 2026Lorenz Hufe, Niclas Griesshaber, Gavin Greif +2History Research Automation
Fraunhofer HHI · University of Oxford
Revisiting the Shape Convention of Transformer Language Models
Feb 6, 2026Feng-Ting Liao, Guan-Ting Yi, Tzu-Quan Lin +2Transformer Architectures Deep Learning Architectures
MediaTek Research · National Taiwan University
Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
Dec 12, 2025Marco Baiesi, Alberto RossoStatistical Physics Generative Models
Department of Physics and Astronomy, University of Padova, Via Marzolo 8, I-35131 Padova, Italy · INFN, Sezione di Padova, Via Marzolo 8, I-35131 Padova, Italy · LPTMS, CNRS, Universit´e Paris-Saclay, 91405, Orsay, France
ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset
May 15, 2025Chengsen Wang, Qi Qi, Zhongwen Rao +2Zero-Shot Forecasting Time Series Foundation Models
Beijing University of Posts and Telecommunications · Huawei Noah’s Ark Lab

Sep 28, 2026, cs.AIJ/K move · Enter open · S save

ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning

Nico Bohlinger, Jan Peters

Technical University of Darmstadt, Germany · Robotics Institute Germany (RIG); German Research Center for AI (DFKI); hessian.AI

Goal-Conditioned Reinforcement Learning Offline Reinforcement Learning Chronos

Open paper AskPDF arXiv

A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Yet, critics in contrastive and survival reinforcement learning do not measure the distances in their representation space in units of time. We therefore introduce ChronoSRL, which gives the critic's embeddings an explicit temporal geometry. The distance between state-action and goal embeddings is trained to match the time that the agent takes to reach the goal (goal-reaching time), while goals that were not reached, and goals from other trajectories, are pushed at least one discount horizon away. Furthermore, reaching a goal quickly once does not mean that reaching it is reliable in general, so the policy should not follow the temporal distance directly. Instead, we build on survival reinforcement learning and predict from our temporal embeddings not only the full distribution of goal-reaching times but also the time spent near the goal. Thereby, the policy is trained to favor actions that reach the goal sooner and more reliably and that keep the agent near it. ChronoSRL learns faster and reaches higher performance than contrastive, action-chunked contrastive, and survival reinforcement learning baselines on seven standard locomotion and navigation benchmarks, even with much smaller networks. To test the limits of self-supervised reinforcement learning, we introduce velocity tracking, goal-position reaching, and box climbing tasks with a quadruped robot in a realistic sim-to-real locomotion setup, and show how the shaping terms that are typical for robotics can be naturally incorporated into our framework. ChronoSRL is the only one of the tested self-supervised reinforcement learning methods that learns to stay at the commanded velocities and goal positions, and climbs the highest boxes.

Momentum

Related topics

Latest papers 39