Energy-Based Models

Ask about this topic

Overview

Energy-based models represent how compatible a data point or configuration is with a task: lower energy generally means greater plausibility, without requiring probabilities to be normalized explicitly. They are trained with methods such as contrastive divergence, noise-contrastive estimation, and score or energy matching, then used for inference and generation with Langevin MCMC, tempering, or diffusion and flow-based samplers. Work spans Boltzmann machines and Hopfield networks as well as image and molecule generation, structured prediction, robotics, and scientific modeling. A central challenge is making sampling and training efficient and reliable; in particular, equilibrium guarantees may not reflect finite-time outputs, and lower energy does not always mean better predictions or reasoning.

Latest papers

CardsList

91 papers9 papers in the last four weeks, up 125% on the four weeks before. 0.1% of all new papers.

  1. Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization

    Oct 26, 2026Ege Demirci, Ambuj SinghLink PredictionGraph Embedding

    Department of Computer Science, UC Santa Barbara Santa Barbara, CA 93106, USA

  2. Scaling Transformer Energy-based Models For High Quality Image Synthesis

    Oct 22, 2026Jungsoo Lee, Alexi Gladstone, Yilun DuImage GenerationEnergy-Based Models

    MIT · UIUC · Harvard University

  3. Probabilistic Energy Modeling Unifies Versatile Swarm Control

    Oct 22, 2026Xiang Zhou, Xiangyu Zhu, Xintong Wang +5Swarm RoboticsRobotic Control

    School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen 518107, China.

  4. First hardware demonstration of a continuous-state probabilistic computer with programmable energy-defined sampling

    Oct 22, 2026Chao Fang, Hsuan Yao Tu, Yihan He +3Energy-Based ModelsConstrained Sampling

    Department of Electrical and Computer Engineering, National University of Singapore, 117583 Singapore · Department of Electronics and Electrical Engineering and Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Industry Academia Innovation School, National Yang-Ming Chiao Tung University, Hsinchu, Taiwan

  5. Learning Graph Energies for Finite-Time Generation

    Oct 14, 2026Amartya Banerjee, Xingyu Xu, Caroline Moosmüller +1Energy-Based ModelsMolecular Graph Generation

  6. Learning Perturbation-Specific Representations through Conditional Energy Prior for Cellular Response Prediction

    Oct 13, 2026Yuchen Yan, Yatao BianSingle-Cell Perturbation ModelingRepresentation Learning

    Department of Computer Science, National University of Singapore

  7. BRACE: Differential Privacy for Dense Associative Memory with LSR Energy

    Oct 8, 2026Chang Qu, Zhaoyang ShiAssociative MemoryDifferential Privacy

    Department of Mathematics and Statistics, University of Ottawa · Center for Applied Mathematics, Fudan University

  8. Nested Power Models for Multirotor Propulsion: From Aerodynamic Drag to Electrical Losses

    Oct 6, 2026Antonio Franchi, Aaron Saini, Ahmed Ali +1Energy-Based Models

    Robotics and Mechatronics group, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands · Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy

  9. Gradient-Free Sampling from Generative Models via Stochastic Bounded Extremum Seeking

    Oct 3, 2026Alexander ScheinkerDiffusion SamplingMarkov Chain Monte Carlo

    Instrumentation and Controls Group Los Alamos National Laboratory Los Alamos, NM 87544, USA

  10. Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory

    Sep 30, 2026Tailia Malloy, Prateek Kumar Rajput, Serge Lionel Nikiema +2Cost-Aware InferenceEnergy-Based Models

    Interdisciplinary Center for Security, Reliability, and Trust, University of Luxembourg, Luxembourg · Department of Social and Decision Sciences, Carnegie Mellon University, Pittsburgh PA

  11. Learning Through Energy Refinement and Manifold Projection: A Cooperative EBM-AE Framework

    Sep 12, 2026Ryad ZemouriGenerative ModelingEnergy-Based Models

    Hydro-Québec 75, boulevard René-Lévesque Ouest Montréal, Québec, Canada

  12. An Energy-Based Conservative-Dissipative Latent Neural Evolution Operator for Magnetization Dynamics

    Sep 3, 2026Sebastian Schaffer, Lukas ExlLatent Dynamics ModelingEnergy-Based Models

    Math. AI/ML, Wolfgang Pauli Institute, Vienna, Austria · Department of Mathematics, University of Vienna, Vienna, Austria

  13. Observation-Conditioned Latent Energy Priors for Sparse Implicit Neural Shape Completion

    Sep 3, 2026Paul Büschl, Ezequiel de la Rosa, Julia Wolleb +3Implicit Neural Representations3D Reconstruction

    Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland · Department of Medical Oncology and Hematology, University Hospital Zurich, Zurich, Switzerland · ETH AI Center, ETH Zurich, Zurich, Switzerland +3

  14. Memory as an Energy Landscape---Hopfield

    Sep 2, 2026Nima DehghaniHopfield NetworksAssociative Memory

    McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA · The NSF AI Institute for Artificial Intelligence and Fundamental Interactions (IAIFI), Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA

  15. STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection

    Aug 20, 2026Jakub Micorek, Mateusz Koziński, Horst PosseggerVideo Anomaly DetectionEnergy-Based Models

    Institute of Visual Computing, Graz University of Technology, Austria · Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Austria

  16. Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields

    Aug 18, 2026Yixuan Sun, Anirban Samaddar, Sandeep MadireddyPhysics-Informed Generative ModelingEnergy-Based Models

    Mathematics and Computer Science, Argonne National Laboratory

  17. Cross-Domain Generalization in Machine Unlearning via Label-Conditioned Energy Magnitude Regularization

    Aug 18, 2026Syed Ali Ahmed, Syed Bilal Ahsan, Muhammad Zaigham ZaheerMachine UnlearningCross-Domain Generalization

    National University of Computer and Emerging Sciences, Karachi, Pakistan · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

  18. Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking

    Aug 18, 2026Swati Rajwal, Sanjay Das, Tirthankar GhosalScientific Idea EvaluationLarge Language Model-Guided Scientific Discovery

    Oak Ridge National Laboratory

  19. Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos

    Aug 17, 2026Mohamed Afham, Christoph Reich, Oliver Hahn +2Video ReasoningInference-Time Optimization

    TU Darmstadt · ELIZA · TU Munich +1

  20. Revisiting Energy-based Tabular Anomaly Detection: Energy and Reconstruction are Complementary

    Aug 14, 2026Junichiro NiimiTabular Anomaly DetectionEnergy-Based Models

    Meijo University, Nagoya Aichi 4688502, Japan

  21. In-Context Density Estimation for Tabular Data

    Aug 10, 2026Patryk Marszałek, Jacek Tabor, Marek ŚmiejaEnergy-Based ModelsUnsupervised Anomaly Detection

    Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland

  22. A Hierarchical Energy-Based Model for Multimodal Cognition

    Aug 8, 2026Subir VarmaComputational Cognitive ModelingCognitive Modeling

    General Cognitics

  23. Comparing SGLD and a fixed-noise predictor-corrector adaptation in canonical joint energy-based models on CIFAR-10

    Aug 5, 2026Dmytro KnopovStochastic Gradient Langevin DynamicsLangevin Dynamics

    Faculty of Computer Sciences, Department of Mathematics, National University of Kyiv-Mohyla Academy, Kyiv, Ukraine.

  24. Thermalizing Stochastic Programs

    Aug 3, 2026Mirko Amico, Andraž Jelinčič, Colin Oscar Nancarrow +6Thermodynamic ComputingEnergy-Efficient ML

    Extropic Corporation, San Francisco, California 94111, USA · CUNY Graduate Center, New York, NY, USA

  25. DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

    Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3AI Agent ReliabilityVLM Interpretability

    University of Electronic Science and Technology of China, Chengdu, China.

  26. Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification

    Jul 30, 2026V. S. Usatyuk, D. A. Sapozhnikov, S. I. EgorovSpectral Graph EmbeddingGraph Representation Learning

    Department of Computer Engineering, South-West State University (SWSU), Kursk, 305040 Russia · T8 LLC, R&D Department, Information Theory Group, Moscow, 107076 Russia

  27. Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

    Jul 29, 2026Nicolas Béreux, Aurélien Decelle, Cyril Furtlehner +1Markov Chain Monte CarloEnergy-Based Models

    Université Paris-Saclay, CNRS, INRIA, LISN, 91190 Gif-sur-Yvette, France · Escuela Técnica Superior de Ingenieros Industriales, Universidad Politécnica de Madrid, 28006 Madrid, Spain · Departamento de Física Teórica & IPARCOS, Universidad Complutense de Madrid, 28040 Madrid, Spain.

  28. Grasp, Handover, Rotate: Bimanual Object Reorientation via Compositional Diffusion and Energy-Based Optimization

    Jul 23, 2026Wun Lam Yeung, Wenjun Liu, Yui Cheung Yu +5Robotic GraspingBimanual Robotic Manipulation

    The Hong Kong University of Science and Technology · Shenzhen Loop Area Institute

  29. A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing

    Jul 17, 2026Owen Lockwood, Jérémy Béjanin, Joost Bus +4Thermodynamic ComputingEnergy-Efficient ML

    Extropic Corporation, San Francisco, California 94111, USA · 2Noumenal Labs Inc, Dallas, Texas 75229, USA · 1Extropic Corporation, San Francisco, California 94111, USA +1

  30. Energy-Based Physics-Informed Form Finding for Clustered Tensegrity Structures

    Jul 14, 2026Jing Qin, Muhao ChenStructural MechanicsEnergy-Based Models

    Department of Mathematics, University of Kentucky, Lexington, KY 40506, USA · Department of Mechanical and Aerospace Engineering, University of Houston, Houston, TX 77204, USA