FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
The Flow has not summarised this story yet — read it at arXiv Machine Learning.
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.
arXiv:2607. 04780v1 Announce Type: cross Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow.
Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow. This paper develops a non-asymptotic error analysis for such SMC samplers.
arXiv:2503. 14549v3 Announce Type: replace-cross Abstract: How can a cheap but biased sequential, finite-horizon sampler over a discrete space be corrected so that its terminal output follows a prescribed Gibbs distribution?
arXiv:2609.37227v1 Announce Type: new Abstract: Inference-time steering adapts pretrained diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or sa...
arXiv:2507. 08390v5 Announce Type: replace Abstract: Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training.