Autoregressive Modeling

Ask about this topic

Overview

Autoregressive models represent a sequence as successive predictions conditioned on earlier elements, enabling both forecasting and generation. Common approaches include Transformer and state-space models, order-agnostic or masked prediction, coarse-to-fine generation, and continuous-latent models. They are used for tasks ranging from language and speech to weather, motion, and physical simulation, with evaluations including long-horizon rollouts and benchmarks such as ERA5, M5, and LibriSpeech. A central challenge is balancing accurate, efficient stepwise prediction with error accumulation, stability, and reliable behavior over long horizons or under distribution shift.

Latest papers

CardsList

86 papers8 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models

    May 5, 2026Wei-Ping Huang, Chee-En Yu, Guan-Ting Lin +1Test-Time AdaptationEntropy Regularization

    Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan

  2. Barriers to Counterfactual Credit Attribution for Autoregressive Models

    May 2, 2026Aloni Cohen, Chenhao ZhangGenerative ModelingCounterfactual Credit Assignment

  3. Sampling two-dimensional spin systems with transformers

    Apr 30, 2026Piotr Białas, Piotr Korcyl, Tomasz Stebel +2TransformerIsing Model

    Institute of Applied Computer Science, Jagiellonian University, ul. Łojasiewicza 11, 30-348 Kraków, Poland · Institute of Theoretical Physics, Jagiellonian University, ul. Łojasiewicza 11, 30-348 Kraków, Poland · Doctoral School of Exact and Natural Sciences, Jagiellonian University, ul. Łojasiewicza 11, 30-348 Kraków, Poland

  4. ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space

    Apr 30, 2026Gabe Guo, Thanawat Sornwanee, Lutong Hao +3Autoregressive DiffusionGenerative Modeling

    Stanford University

  5. A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting

    Apr 22, 2026Brooks Kinch, Xiaozhe Hu, Yilong Huang +6Neural Surrogate ModelingTime Series Transformers

    Mechanical Engineering and Applied Mechanics, University of Pennsylvania, Philadelphia, PA, USA · Department of Mathematics, Tufts University, Medford, MA, USA · Department of Mathematics and Cybernetics, SINTEF Digital, Oslo, Norway +3

  6. One Scale at a Time: Scale-Autoregressive Modeling for Fluid Flow Distributions

    Apr 13, 2026Mario Lino, Nils ThuereyGenerative ModelingAutoregressive Modeling

    Technical University of Munich

  7. Hidden Biases in Conditioning Autoregressive Models

    Apr 9, 2026Francois Pachet, Pierre RoyConstrained Generative ModelingConstrained Decoding

    LIP6, Sorbonne Université · Soundtrap

  8. Towards Scaling Law Analysis For Spatiotemporal Weather Data

    Apr 6, 2026Alexander Kiefer, Prasanna Balaprakash, Xiao WangWeather ForecastingSpatiotemporal Forecasting

    Bredesen Center, University of Tennessee, Knoxville, Tennessee · Oak Ridge National Laboratory, Oak Ridge, Tennessee

  9. Next-Scale Autoregressive Models for Text-to-Motion Generation

    Apr 4, 2026Zhiwei Zheng, Shibo Jin, Lingjie Liu +1Text-to-Motion GenerationHuman Motion Generation

    University of Pennsylvania

  10. From Causal Discovery to Dynamic Causal Inference in Neural Time Series

    Mar 21, 2026Dmitry Zaytsev, Valentina Kuskova, Michael CoppedgeCausal InferenceTime-Series Causal Discovery

    Lucy Family Institute for Data & Society, University of Notre Dame, Notre Dame, Indiana, USA · Political Science, University of Notre Dame, Notre Dame, Indiana, USA

  11. Revisiting Autoregressive Models for Generative Image Classification

    Mar 19, 2026Ilia Sudakov, Artem Babenko, Dmitry BaranchukVisual Autoregressive ModelsImage Classification

    1HSE University · 2Yandex Research

  12. Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation

    Mar 19, 2026Anaísa Lucena, Ana Martins, Armando J. Pinho +1Autoregressive Modeling

    IEETA/DETI/LASI, University of Aveiro, 3810-193 Aveiro, Portugal

  13. Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems

    Mar 18, 2026Qi Liu, Laure Zanna, Joan BrunaNeural Surrogate ModelingAutoregressive Modeling

    Courant Institute School of Mathematics, Computing, and Data Science, New York University, USA.

  14. Scaling Autoregressive Models for Lattice Thermodynamics

    Mar 16, 2026Xiaochen Du, Juno Nam, Sulin Liu +1Autoregressive ModelingComputational Materials Science

    Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA

  15. Data-Driven Autoregressive Power Prediction for GTernal Robots in the Robotarium

    Mar 14, 2026Yassin Abdelmeguid, Ammar HasanAutoregressive ModelingMobile Robotics

    American University of Sharjah

  16. ARCHE: Autoregressive Residual Compression with Hyperprior and Excitation

    Mar 10, 2026Sofia Iliopoulou, Dimitris Ampeliotis, Athanassios SkodrasLearned Image CompressionAutoregressive Modeling

    Dept. of Electrical and Computer Engineering, University of Patras, Patras, Greece · Dept. of Digital Media and Communication, Ionian University, Argostoli, Greece

  17. On the Feasibility and Opportunity of Autoregressive 3D Object Detection

    Mar 9, 2026Zanming Huang, Jinsu Yoo, Sooyoung Jeon +6Lidar-Based 3D Object Detection3D Object Detection

    The Ohio State University · Cornell University · Boston University +1

  18. NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving

    Mar 6, 2026Kai Luo, Xu Wang, Rui Fan +1Visual Object TrackingAutonomous Driving

    School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha 410082, China · College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China · State Key Laboratory of Intelligent Autonomous Systems, Tongji University, Shanghai 201804, China

  19. Spatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detection

    Mar 3, 2026Ertunc Erdil, Nico Schulthess, Guney Tombak +1Medical Image Anomaly DetectionIndustrial Anomaly Detection

    Computer Vision Lab. ETH Zurich, Zurich, Switzerland

  20. Embedding interpretable ℓ1\ell_1-regression into neural networks for uncovering temporal structure in cell imaging

    Mar 3, 2026Fabian Kabus, Maren Hackenberg, Julia Hindel +6Autoregressive ModelingNeural Network Interpretability

    Institute of Medical Biometry and Statistics (IMBI), Faculty of Medicine and Medical Center, University of Freiburg, Germany · Department of Computer Science, University of Freiburg, Germany · Institute of Physiology I, Faculty of Medicine, University of Freiburg, Germany +2

  21. Switch-Hurdle: A MoE Encoder with AR Hurdle Decoder for Intermittent Demand Forecasting

    Feb 26, 2026Fabian Muşat, Simona CăbuzTime Series ForecastingProbabilistic Time Series Forecasting

    eMAG, Romania

  22. Selecting Optimal Variable Order in Autoregressive Ising Models

    Feb 23, 2026Shiba Biswal, Marc Vuffray, Andrey Y. LokhovAutoregressive ModelingIsing Model

    Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM 87545.

  23. BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression

    Feb 18, 2026Mingzhe Cui, Tao Chen, Yang Jiao +4EEG Foundation ModelsSelf-Supervised Time Series Representation Learning

    State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China · Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

  24. Why Any-Order Autoregressive Models Need Two-Stream Attention: A Structural-Semantic Tradeoff

    Feb 17, 2026Patrick Pynadath, Ruqi ZhangAutoregressive ModelingSelf-Attention

    Department of Computer Science, Purdue University

  25. ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching

    Sep 19, 2025Graham Clyne, Guillaume Couairon, Guillaume Gastineau +2Neural Surrogate ModelingClimate Science

    ARCHES, INRIA, Paris, France · UMR LOCEAN, IPSL, Sorbonne Universit´e, IRD, CNRS, MNHN, Paris, France · Department of Computer Science, University of Colorado Boulder, USA

  26. Temporal horizons in forecasting: a performance-learnability trade-off

    Jun 4, 2025Pau Vilimelis Aceituno, Jack William Miller, Noah Marti +2Long-Term Time Series ForecastingTime Series Forecasting

    Institute of Neuroinformatics, ETH Zürich and University of Zürich, Winterhurerstrasse 190, Zürich 8057, Switzerland · School of Computing, National Australian University, 108 North Rd, Acton ACT 2601, Australia · Unit of Land Change Science, Swiss Federal Research Institute for Forest, Snow and Landscape Zürcherstrasse 111, Birmensdorf 8903, Switzerland