paper-with-me

Papers

SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation

2026-05-18 · Longtao Jiang, Jianmin Bao, Zhendong Wang, Xin Tao, Pengfei Wan, Zhihui Li, Xiaojun Chang arxiv

Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single invertible transport over the full ambient space, making them highly sensitive to high-dimensional representations. This leads to a semantic-capacity mismatch in modern visual representation spaces, where semantic information is compact but encoded in overcomplete features. We propose SRC-Flow, which introduces a Semantic Representation Compressor (SRC) to compact high-dimensional RAE features into a low-dimensional semantic space before flow modeling and preserve reconstruction through the frozen RAE decoder. This compact space reduces the modeling burden of NFs and enables effective likelihood-based generation in semantic representation space. We further adopt constant noise regularization tailored to the fixed unconditional bijection learned by flows. On ImageNet $256 \times 256$ and $512 \times 512$, SRC-Flow achieves state-of-the-art generation quality among normalizing flow methods, with gFID scores of 1.65 and 2.07 under classifier-free guidance, while retaining exact likelihood computation in the compact semantic representation space and deterministic invertible sampling at the flow level. Codes and models will be available at https://github.com/longtaojiang/SRC-Flow.

📄 PDF Abstract BibTeX arXiv:2605.18267

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Ordering Dimensions with Nested Dropout Normalizing Flows

2020-06-15 · Artur Bekasov, Iain Murray

The latent space of normalizing flows must be of the same dimensionality as their output space. This constraint presents a problem if we want to learn low-dimensional, semantically meaningful representations. Recent work…

From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows

2026-02-06 · Daniel Galperin, Ullrich Köthe arxiv

Learning unsupervised representations that are both semantically meaningful and stable across runs remains a central challenge in modern representation learning. We introduce entropy-ordered flows (EOFlows), a normalizin…

Representation Learning

Boosting Summarization with Normalizing Flows and Aggressive Training

2023-11-01 · Yu Yang, Xiaotong Shen

This paper presents FlowSUM, a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization. Our approach tackles two primary challenges in variational summarization: insufficient sem…

DecoderKnowledge DistillationText Summarization

Unsupervised Learning of PCFGs with Normalizing Flow

2019-07-01 · ACL 2019 7 · Lifeng Jin, Finale Doshi-Velez, Timothy Miller, Lane Schwartz 외

Unsupervised PCFG inducers hypothesize sets of compact context-free rules as explanations for sentences. PCFG induction not only provides tools for low-resource languages, but also plays an important role in modeling lan…

Language Acquisition

Latent Reasoning with Normalizing Flows

2026-06-04 · Guancheng Tu, Xiangjun Fu, Suhao Yu, Yao Tang 외 arxiv

Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. However, textual CoT forces this computation through a discrete, seri…