stat.MLOct 3, 2026

Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering

Authors: Ziseok Lee, Jaehyeon Kim, Seungwon Kim, Seunghyun Moon, Haneul Choi, Wooyeol Lee, Donghyun Koh, Minhyeong Lee, 

Organizations: Seoul National University · Asteromorph

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Inference-time steering combines pretrained diffusion experts or rewards without retraining by changing the dynamics that transport noise to data. Feynman-Kac correction compensates for proposal mismatch through importance-weighted sequential Monte Carlo (SMC), whose finite-particle behavior depends on the proposal. Variance-controlling guidance (VCG) improves that proposal by fitting a linear drift correction to minimize empirical log-weight-rate variance. Although its population optimum cannot worsen residual variance, finite-particle VCG can nearly eliminate its fitting residual while increasing residual risk on new states by orders of magnitude. The resulting update can degrade unweighted generation or accelerate particle collapse. We show that the centered Feynman-Kac rate is the normalized transport residual and that expected out-of-fit benefit is exactly population headroom minus coefficient-estimation penalty. Under regularity assumptions, a Wasserstein analysis bounds the unweighted proposal's terminal error using this residual. These results motivate Risk-Calibrated Proposal Transport (RCPT), which uses deletion leave-one-out residuals to calibrate the retained fraction of the VCG update, adding no model calls and only small linear-algebra overhead. Experiments on 2D checker distributions, scaffold decoration, molecular property optimization, and class-conditional CIFAR-10 generation demonstrate recovery from harmful fitted updates. Across molecular and image domains, RCPT mitigates harmful fitted updates and improves a broad range of terminal metrics relative to uncalibrated VCG.

More in this topic

Inference-Time Guidance

Inference-time guidance steers pretrained generative models, language models, and policies toward desired outputs without requiring full retraining.

See all 104 papers

Explore similar work

CardsList
Sep 28, 2026

FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models

Many inference-time tasks for pretrained discrete diffusion models and diffusion language models reduce to drawing samples from a tilted version of the pretrained distribution. Feynman-Kac sequential Monte Carlo (SMC) makes this correction exact in principle, but its prescribed weights routinely degenerate when the proposal dynamics are misaligned with the tilt, capping the practical gains from additional particles. We introduce FluxLite, a lightweight, training-free proposal-control framework for discrete diffusion. On the sparse directed graph of pretrained reverse rates, any sparse jump-rate perturbation can be exactly compensated by a qtq_t-weighted graph-divergence term in the Feynman-Kac potential; the target path is therefore preserved while the residual reweighting variance becomes a local convex objective. We instantiate this principle as two practical samplers: a one-hop local reallocation rule (HEU) and a small nonnegative quadratic program over pretrained-rate bases (D-VCG). We further prove population stability under the standard score-entropy training loss, identifying a tilted-path coverage factor that governs robustness to score error, together with finite-particle convergence for a fixed controlled Feynman-Kac recursion. Empirically, FluxLite improves over standard Feynman-Kac SMC baselines by up to two orders of magnitude in terminal KL on an analytically tractable finite-state CTMC benchmark, and reduces row-correlation MSE on 2D Ising sampling by 5-7x in geometric mean and up to 55x at peak.

Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff +2

Kempner Institute Harvard University · ICME Stanford University · Department of Chemistry Stanford University +2

Diffusion SamplingDiffusion ModelsMarkov Chain Monte CarloDiffusion Language Models
AskPDF
Sep 29, 2026

Interacting particle guidance for sampling reward-tilted generative priors

Inference-time steering adapts pretrained diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or samples with desired properties, without retraining. This can be formalized as sampling from a reward-tilted generative prior. As exact sampling from this distribution is intractable, guidance-based methods rely on approximations producing biased samples, and sequential Monte Carlo (SMC) methods correct for this bias using importance weights. However, while exact in the large particle limit, SMC suffers from weight degeneracy and particle collapse in practice. We propose interacting particle guidance (IPG), which replaces reweighting with transport. The particles interact through an additional drift, derived from the Feynman--Kac PDE to cancel the reweighting term, and remain unweighted. Choosing the drift in a reproducing kernel Hilbert space yields a closed-form solution that is cheap to compute, with negligible overhead compared to SMC. We demonstrate the method on Gaussian mixtures with known posteriors, and on high-dimensional image inpainting and protein structure inference tasks.

Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund +1

Linköping University, Sweden · Uppsala University, Sweden

Inference-Time Guidance
AskPDF
Apr 8, 2026

VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion

Sequential Monte Carlo (SMC) samplers for reward-guided diffusion models often suffer from rapid lineage collapse: a few high-reward particles dominate the population within a handful of resampling steps, destroying diversity and degrading sample quality. We propose a variance-decomposition framework for reward-guided diffusion SMC that separates continuation variance VtcontV_t^{\mathrm{cont}} from residual variance VtresV_t^{\mathrm{res}}, revealing that high offspring-count variance under the commonly used multinomial resampling drives this collapse. This motivates VASR (Variance-Aware Systematic Resampling), which addresses both variance terms via variance-optimal mass allocation mt∝wtertm_t \propto w_t e^{r_t} (minimizing VtcontV_t^{\mathrm{cont}}) and systematic resampling (controlling VtresV_t^{\mathrm{res}}). For latent diffusion models where intermediate rewards are noisy due to stochastic continuations, we propose VASR-Max, a deliberately biased high-selection variant for variance-sensitive reward optimization. Both methods are training-free, fully parallelizable, and add only linear overhead. On MNIST and CIFAR-10, VASR achieves as high as 26%26\% better FID than prior SMC methods while remaining 66 times faster than MCTS-based value methods at matched compute. On text-to-image generation, VASR-Max consistently outperforms the strongest SMC baseline across compute budgets and matches MCTS-based methods within 2.5--3% reward at high budgets while being approximately times faster.

Shivanshu Shekhar, Sagnik Mukherjee, Jia Yi Zhang +1

Siebel School of Computing and Data Science University of Illinois Urbana-Champaign · Department of Statistics University of Illinois Urbana-Champaign

Diffusion Model SamplingDiffusion SamplingDiffusion Model Guidance
AskPDF