REVIEW 8 cited by
Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
read the original abstract
Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering methods suffer from inaccurate value estimation, especially at high noise levels, which biases guidance. Moreover, information from past runs is not reused to improve sample quality, resulting in inefficient use of compute. Inspired by the success of Monte Carlo Tree Search, we address these limitations by casting inference-time alignment as a search problem that reuses past computations. We introduce a tree-based approach that samples from the reward-aligned target density by propagating terminal rewards back through the diffusion chain and iteratively refining value estimates with each additional generation. Our proposed method, Diffusion Tree Sampling (DTS), produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant, Diffusion Tree Search (DTS$^\star$), performs a global search for high reward samples. On MNIST and CIFAR-10 class-conditional generation, DTS matches the FID of the best-performing baseline with up to $10\times$ less compute. In text-to-image generation and language completion tasks, DTS$^\star$ effectively searches for high reward samples that match best-of-N with up to $5\times$ less compute. By reusing information from previous generations, we get an anytime algorithm that turns additional compute into steadily better samples, providing a scalable approach for inference-time alignment of diffusion models.
Forward citations
Cited by 8 Pith papers
-
Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search
Bootstrap Flow-Map Trees construct complete DDPM-like trajectories with a single NFE and dynamic steps, enabling efficient online feedback-driven search and alignment that beats prior tree and SMC samplers.
-
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
PNAPO augments preference data with prior noise pairs and uses straight-line interpolation to create a tighter surrogate objective for offline alignment of rectified flow models.
-
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
FVD applies Fleming-Viot population dynamics to diffusion model sampling at inference time to reduce diversity collapse while improving reward alignment and FID scores.
-
Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
IMPFM is a multi-particle flow-map sampling method with sequential posterior sharing and interaction-aware correction that targets a KL-tilted distribution for global exploration in online feedback search.
-
Few-step Cofolding with All-Atom Flow Maps
DeCAF distills all-atom cofolding diffusion models into few-step flow maps, showing improved or matched accuracy on protein-ligand tasks with 5x fewer inference steps.
-
Multimodal Diffusion to Mutually Enhance Polarized Light and Low Resolution EBSD Data
A multimodal diffusion model trained on synthetic data enhances low-resolution EBSD and corrupted polarized light data, achieving near full-resolution performance with only 25% EBSD data.
-
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
VASR separates continuation and residual variance in reward-guided diffusion SMC, using optimal mass allocation and systematic resampling to achieve up to 26% better FID scores and faster runtimes than prior SMC and M...
-
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.