paper-with-me

홈 › Papers

Structured State-Space Regularization for Generation-Friendly Image Tokenization

2026-04-13 · Jinsung Lee, Jaemin Oh, Namhun Kim, Dongwon Kim, Byung-Jun Yoon, Suha Kwak arxiv

Image tokenizers play a central role in modern generative models, where the structure of the latent space critically determines the downstream generation performance. A key but underexplored property of effective latent representations is spectral organization, the ability to encode information across frequency components. In this work, we introduce structured state-space regularization, a principled approach to inducing spectral structure in latent spaces. We derive a regularization objective by revisiting state-space models (SSMs) as systems mimicking a basis function's behavior. This perspective reveals that hidden states of SSMs are induced to capture the frequency components, resulting in a novel regularizer that enforces the latent space to capture spectral structure of images. Experiments demonstrate that our regularizer improves the generative performance of image tokenizers while incurring only minimal loss in their reconstruction fidelity.

📄 PDF Abstract BibTeX arXiv:2604.11089

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Boosting Latent Diffusion Models via Disentangled Representation Alignment

2026-01-09 · John Page, Xuesong Niu, Kai Wu, Kun Gai arxiv

Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs b…

Image Generation

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

2026-05-08 · Zhengrong Yue, Taihang Hu, Mengting Chen, Haiyu Zhang 외 arxiv

Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing tokenizers are primarily designed to improve reconstruction fidelity or …

Structured Pruning for Deep Convolutional Neural Networks: A survey

2023-03-01 · Yang He, Lingao Xiao

The remarkable performance of deep Convolutional neural networks (CNNs) is generally attributed to their deeper and wider architectures, which can come with significant computational costs. Pruning neural networks has th…

Network PruningNeural Architecture SearchSurvey

Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization

2026-02-07 · Xi Chen, Ming Li, Junxi Li, Changsheng Li 외 arxiv

Weight-only post-training quantization (PTQ) is crucial for efficient Large Language Model (LLM) deployment but suffers from accuracy degradation caused by weight and activation outliers. Existing mitigation strategies o…

IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking

2024-10-09 · Shubham Ugare, Rohan Gumaste, Tarun Suresh, Gagandeep Singh 외

Large Language Models (LLMs) are widely used for tasks such as natural language and code generation, but their outputs often suffer from issues like hallucination, toxicity, and incorrect results. Current libraries for s…

ARCCode GenerationHallucination