Pith. sign in

REVIEW 4 cited by

Amortizing intractable inference in diffusion models for vision, language, and control

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

arxiv 2405.20971 v2 pith:QAFZJGFF submitted 2024-05-31 cs.LG cs.CV

classification cs.LGcs.CV
keywords diffusionmathbflearningbalancegenerativeinferencelanguagemodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data, $\mathbf{x}\sim p^{\rm post}(\mathbf{x})\propto p(\mathbf{x})r(\mathbf{x})$, in a model that consists of a diffusion generative model prior $p(\mathbf{x})$ and a black-box constraint or likelihood function $r(\mathbf{x})$. We state and prove the asymptotic correctness of a data-free learning objective, relative trajectory balance, for training a diffusion model that samples from this posterior, a problem that existing methods solve only approximately or in restricted cases. Relative trajectory balance arises from the generative flow network perspective on diffusion models, which allows the use of deep reinforcement learning techniques to improve mode coverage. Experiments illustrate the broad potential of unbiased inference of arbitrary posteriors under diffusion priors: in vision (classifier guidance), language (infilling under a discrete diffusion LLM), and multimodal data (text-to-image generation). Beyond generative modeling, we apply relative trajectory balance to the problem of continuous control with a score-based behavior prior, achieving state-of-the-art results on benchmarks in offline reinforcement learning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework

    cs.HC 2025-08 unverdicted novelty 5.0 of 10

    A three-layer framework (input, processing, output) for adaptive external human-machine interfaces in autonomous vehicles is introduced to systematize design and analysis.

  2. ADEPT: Adaptive Diffusion Environment for Policy Transfer Sim-to-Real

    cs.RO 2025-06 conditional novelty 5.0 of 10

    An adaptive curriculum that steers a pretrained diffusion terrain generator via policy success-weighted latent blending improves zero-shot sim-to-real off-road navigation performance.

  3. Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control

    cs.LG 2025-02 conditional novelty 4.0 of 10

    Frequency-filtered noise in the diffusion forward process steers what the denoiser learns, yielding modest FID gains on some datasets and partial recovery after known-band corruption.

  4. Why Pool When You Can Flow? Active Learning with GFlowNets

    cs.LG 2025-08 conditional novelty 3.0 of 10

    Training a GFlowNet to generate high-BALD molecules gives pool-size-independent acquisition and near-BALD classification quality on JAK2 virtual screening.

Pith tools