{"paper":{"title":"Structured State-Space Regularization for Generation-Friendly Image Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A regularizer that makes image tokenizers mimic state-space model dynamics produces more compact and generation-friendly latent spaces.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byung-Jun Yoon, Dongwon Kim, Jaemin Oh, Jinsung Lee, Namhun Kim, Suha Kwak","submitted_at":"2026-04-13T07:10:17Z","abstract_excerpt":"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 perspe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our regularizer enforces encoding of fine spatial structures and frequency-domain cues into compact latent features; leading to more effective use of representation capacity and improved generative modelability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That guiding tokenizers to mimic SSM hidden-state dynamics will reliably transfer frequency awareness and spatial structure encoding to image latents without introducing new artifacts or requiring dataset-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A new regularizer transfers frequency awareness from state-space models into image tokenizers, yielding more compact latents that improve diffusion-model generation quality with little reconstruction penalty.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A regularizer that makes image tokenizers mimic state-space model dynamics produces more compact and generation-friendly latent spaces.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2dbbd7c7ca5479fb3a7c114f7b06749d9e3fb28ef91de225e52e24168d1b340d"},"source":{"id":"2604.11089","kind":"arxiv","version":2},"verdict":{"id":"8341ea24-3b55-4798-9fb5-d28e9cfa61cc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:50:13.488145Z","strongest_claim":"our regularizer enforces encoding of fine spatial structures and frequency-domain cues into compact latent features; leading to more effective use of representation capacity and improved generative modelability.","one_line_summary":"A new regularizer transfers frequency awareness from state-space models into image tokenizers, yielding more compact latents that improve diffusion-model generation quality with little reconstruction penalty.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That guiding tokenizers to mimic SSM hidden-state dynamics will reliably transfer frequency awareness and spatial structure encoding to image latents without introducing new artifacts or requiring dataset-specific tuning.","pith_extraction_headline":"A regularizer that makes image tokenizers mimic state-space model dynamics produces more compact and generation-friendly latent spaces."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11089/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}