Metraipolis › archive › dc_9925dc4e26cf

PATTS: Parallel-Aware Test-Time Scaling for Thought-Image Generation in Multimodal Discrete Diffusion LLMs — arXiv:2611.04948

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04948
License (as archived): CC0-1.0
Archived: 2026-11-04T12:57:19.105Z
SHA-256 of the archived text: 68def81853378997e3196c85b7f530d99c30bc231cf9b839967e8169b27ded05
Stable URL of this page: https://metraipolis.com/documento/dc_9925dc4e26cf

How to cite

PATTS: Parallel-Aware Test-Time Scaling for Thought-Image Generation in Multimodal Discrete Diffusion LLMs — arXiv:2611.04948 — arXiv (en), https://arxiv.org/abs/2611.04948 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9925dc4e26cf (Metraipolis archive dc_9925dc4e26cf, sha256 68def81853378997e3196c85b7f530d99c30bc231cf9b839967e8169b27ded05)

BibTeX

@misc{dc9925dc4e26cf,
  title = {PATTS: Parallel-Aware Test-Time Scaling for Thought-Image Generation in Multimodal Discrete Diffusion LLMs — arXiv:2611.04948},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04948},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9925dc4e26cf; sha256 68def81853378997e3196c85b7f530d99c30bc231cf9b839967e8169b27ded05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04948. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Test-time scaling (TTS) improves generative models by allocating additional inference-time computation to sampling, search, and verification. Existing image generation approaches, however, typically rank completed images or image-centric intermediate states. We study TTS for parallel multimodal discrete diffusion language models, in which reasoning tokens and image tokens are decoded jointly within a single generation trajectory. We first diagnose a limitation of conventional final-image selection: on GenEval, a CLIP-style image-prompt score is weakly aligned with within-prompt compositional correctness, leaving substantial headroom between verifier selection and oracle selection. We then propose PATTS, a novel parallel-aware TTS framework that searches over intermediate thought-image states using cross-modal verifier signals. PATTS uses a state-dependent reliability weight, derived from model-internal trajectory diagnostics, to modulate the influence of external semantic verification during generation. In the fixed N=32 evaluation on MMaDA-Parallel, the PATTS reaches a GenEval score of 0.844, compared with 0.628 without TTS, 0.787 for Best-of-N, and 0.810 for FKD. These results show that reliability-aware trajectory verification can improve test-time selection for parallel thought-image co-generation under the evaluated search budget. Our code release is at this https URL

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.04948 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:33:47.200Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).