arXiv:2604. 02121v2 Announce Type: replace-cross Abstract: Stochastic kinetic models are ubiquitous in physics, yet inferring their parameters from experimental data remains challenging.
arXiv:2604. 13213v2 Announce Type: replace-cross Abstract: Rare events such as conformational changes in biomolecules, phase transitions, and chemical reactions are central to the behavior of many physical systems, yet they are extremely difficult to study computationally because unbiased simulations seldom produce them.
The paper introduces GenAIMMD, an iterative algorithm that learns the committor function and trains a conditioned Boltzmann Generator to generate uncorrelated transition paths without prior knowledge of the reaction coordinate. This method combines transition path sampling with committor learning, enabling fully parallelizable sampling. Benchmarks on a toy model and a polymer system show a substantial performance improvement over standard TPS.
arXiv:2607. 12922v1 Announce Type: cross Abstract: Stochastic-process models are, as a rule, far easier to simulate than to condition.
arXiv:2607. 15682v1 Announce Type: new Abstract: Sampling from an unnormalized Boltzmann density requires proposals that move probability mass globally while retaining enough path-probability information for statistical correction.
Studying the dynamical behavior of a system often depends on characterizing how it transitions between long-lived states. Because such transitions are rare, observing them usually requires specialized...
Stochastic-process models are, as a rule, far easier to simulate than to condition. Non-linear observations, non-Gaussian likelihoods, black-box information, and global constraints all induce intractable conditional laws, requiring bespoke, model-specific constructions.
arXiv:2609.37043v1 Announce Type: new Abstract: Sampling from unnormalized distributions over large discrete state spaces becomes difficult when a multimodal target is far from a tractable reference....
VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion proposes a new inference-time framework that improves steering of frozen masked discrete diffusion models. By reducing the variance of guidance estimates, applying reward tilting to clean-token logits, and adapting the selection temperature at each step, VGAS addresses three default choices in existing pipelines. Experiments on regulatory DNA, protein, and small-molecule benchmarks show that VGAS achieves the best training-free reward performance and matches or surpasses reward-fine-tuned generators.
arXiv:2512.10309v3 Announce Type: replace-cross Abstract: Chemical reaction networks are widely used to model stochastic dynamics in biophysical processes. Their exact probabilistic description via t...
ENCORE is a new exact parallel control method for inference‑time steering of pretrained generative models toward tilted target distributions. It uses replica exchange with each replica storing its trajectory, avoiding simulation of the intractable time reversal and ensuring target invariance. Experiments on synthetic, biomolecular, and image data show that ENCORE achieves competitive accuracy and diversity, remains robust to sampler perturbations, and works with distilled samplers where prior replica‑exchange corrections fail.
CRNDiff is a new count‑native diffusion framework that uses stochastic chemical reaction networks to model nonnegative integer data such as single‑cell RNA sequencing. It provides a closed‑form forward‑noising kernel, enabling efficient reverse sampling via forward‑filtering backward‑sampling and data‑driven selection of the terminal noising time. The method also introduces tilted Feynman–Kac steering to sample rare subpopulations without retraining, and demonstrates superior conditional fidelity and marker‑level preservation on human heart scRNA‑seq data.