Hugging Face Trending Papers July 29, 2026

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

Read the original on Hugging Face Trending Papers →

Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability. We introduce a training algorithm based on Parallel Trajectory Tempering (PTT), which exploits the continuity of the optimization path to maintain equilibrium sampling throughout learning.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 30

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

arXiv:2607. 27077v1 Announce Type: new Abstract: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability.

By Nicolas B\'ereux, Aur\'elien Decelle, Cyril Furtlehner, Beatriz Seoane

multimodal benchmarks

arXiv Machine Learning

Aug 6

Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization

arXiv:2602. 03729v3 Announce Type: replace Abstract: Sampling from unnormalized probability densities is a central challenge in computational science.

By Henrik Schopmans, Christopher von Klitzing, Pascal Friederich

benchmarks

arXiv Machine Learning

Jun 2

Scalable Inference-Time Annealing with Surrogate Likelihood Estimators

arXiv:2605. 31498v2 Announce Type: replace Abstract: A long standing challenge in computational chemistry and biophysics is efficiently sampling the Boltzmann distribution of molecules.

By Daniel Pe\~naherrera, Rishal Aggarwal, David Ryan Koes

diffusion fine-tuning benchmarks

arXiv Machine Learning

Jul 23

Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes

arXiv:2601. 21026v2 Announce Type: replace-cross Abstract: Sampling configurations at thermodynamic equilibrium is a central challenge in statistical physics.

By Louis Grenioux, Maxence Noble

diffusion multimodal

arXiv Machine Learning

Aug 11

Leveraging generative models to assist Monte Carlo sampling

arXiv:2608. 07648v1 Announce Type: cross Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to statistical physics and molecular simulation.

By Marylou Gabri\'e

diffusion multimodal

arXiv Machine Learning

Jun 30

Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

arXiv:2606. 29110v1 Announce Type: new Abstract: Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations.

By RuiKang OuYang, Hanlin Yu, Xinyue Ai, Yutong He, Nicholas M. Boffi, Pradeep Ravikumar, Jose Miguel Hernandez-Lobato, Max Simchowitz, Benjamin Kurt Miller, Omar Chehab

efficiency benchmarks

Related stories

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization

Scalable Inference-Time Annealing with Surrogate Likelihood Estimators

Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes

Leveraging generative models to assist Monte Carlo sampling

Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps