Pith. sign in

REVIEW 4 cited by

Jet: A Modern Transformer-Based Normalizing Flow

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2412.15129 v1 pith:FHKJ6ODJ submitted 2024-12-19 cs.CV cs.AIcs.LG

Alexander Kolesnikov , André Susano Pinto , Michael Tschannen This is my paper
classification cs.CVcs.AIcs.LG
keywords modelsnormalizingflowgenerativearchitecturedesignflowsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In the past, normalizing generative flows have emerged as a promising class of generative models for natural images. This type of model has many modeling advantages: the ability to efficiently compute log-likelihood of the input data, fast generation and simple overall structure. Normalizing flows remained a topic of active research but later fell out of favor, as visual quality of the samples was not competitive with other model classes, such as GANs, VQ-VAE-based approaches or diffusion models. In this paper we revisit the design of the coupling-based normalizing flow models by carefully ablating prior design choices and using computational blocks based on the Vision Transformer architecture, not convolutional neural networks. As a result, we achieve state-of-the-art quantitative and qualitative performance with a much simpler architecture. While the overall visual quality is still behind the current state-of-the-art models, we argue that strong normalizing flow models can help advancing research frontier by serving as building components of more powerful generative models.

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.

  1. Adaptive Order Policies for Masked Diffusion

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.

  2. SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

    cs.RO 2026-02 unverdicted novelty 6.0 of 10

    SERNF achieves sample-efficient real-world fine-tuning of multimodal dexterous policies by pairing exact-likelihood normalizing flow policies with action-chunked value critics.

  3. SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

    cs.RO 2026-02 conditional novelty 6.0 of 10

    SERNF fine-tunes dexterous manipulation policies on real hardware by pairing normalizing-flow policies with action-chunked critics and conservative off-policy RL.

  4. Fractal Flow: Hierarchical and Interpretable Normalizing Flow via Topic Modeling and Recursive Strategy

    stat.ML 2025-08 reject novelty 4.0 of 10

    Fractal Flow combines a Dirichlet-topic latent prior with recursive coupling layers in a normalizing flow, reporting lower bits-per-dim than a custom RealNVP baseline on MNIST and FashionMNIST.

Pith tools