← Back to all news
arXiv Machine Learning

WASABI: Wasserstein Sampling via Bridge Interpolants

WASABI (Wasserstein Sampling via Bridge Interpolants) is a diffusion‑model based method for sampling from Boltzmann distributions using only the energy function. It trains the model by minimizing the KL divergence to the target distribution through Wasserstein gradient flows, avoiding the need to compute the model’s log‑density gradient. After training, WASABI can generate new samples without further energy or gradient evaluations, achieving superior performance on alanine dipeptide and competitive results on interacting particle benchmarks.

Related stories

arXiv Machine Learning
Sep 25

Neural Transport Nested Sampling

Neural Transport Nested Sampling (NTNS) is a new sampling algorithm that merges nested sampling with neural flow-based methods to sample from Boltzmann distributions of molecular systems. It employs a flow-matching velocity as the drift in a Metropolis–Hastings corrected Langevin kernel within a nested sampling loop, requiring only target energy evaluations and enabling scalable estimation of the full partition function for high-dimensional particle systems. Benchmarks on Lennard–Jones clusters up to 55 particles show NTNS reduces interatomic distance and energy Wasserstein errors by more than an order of magnitude compared to leading neural baselines, while also providing a calibrated, temperature-resolved partition function estimate that captures phase structure from a single run.

By David Yallup, Will Handley
diffusionbenchmarks
More like this →
arXiv Machine Learning
Aug 10

Sampling via Stochastic Interpolants by Langevin-based Velocity and Initialization Estimation in Flow ODEs

arXiv:2601. 08527v3 Announce Type: replace-cross Abstract: We propose a novel method for sampling from unnormalized Boltzmann densities based on a probability flow ordinary differential equation (ODE) derived from linear stochastic interpolants.

By Chenguang Duan, Yuling Jiao, Gabriele Steidl, Christian Wald, Jerry Zhijian Yang, Ruizhe Zhang
multimodal
More like this →
arXiv AI
Oct 2

Discrete Wasserstein Flows for One-Step Generative Modeling

The paper presents a new one‑step generative modeling framework for finite state spaces, leveraging discrete Wasserstein geometry to define a target‑relative KL gradient flow over a reversible Markov kernel. The authors implement this flow at the particle level using Markov jumps and encode the resulting transport updates into a latent‑conditioned generator, enabling one‑step inference after training. Experiments on a controlled setting confirm KL dissipation, consistency between particle dynamics and probability flow, and accurate numerical scaling, while a finite‑capacity neural generator successfully tracks the exact transport targets.

By Alessandro Micheli, Andrea Zerio, Samir Bhatt
More like this →
arXiv Statistics ML
Oct 2

Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models

The paper introduces the Energy-based Feynman-Kac Corrector (EBFKC), a method that improves inference-time scaling for diffusion models that are imperfect due to data and training limitations. EBFKC derives Feynman-Kac dynamics to exactly track a prescribed path in continuous time, then approximates these dynamics with sequential Monte Carlo and variance‑controlling guidance. Experiments on Gaussian mixtures, particle systems, and molecular simulations demonstrate that EBFKC closely matches target distributions and free‑energy profiles, outperforming standard inference‑time scaling baselines that still exhibit significant sampling errors.

By Zuokai Wen, Louis Grenioux, Weinan E, Jiequn Han
diffusion
More like this →