Metraipolis › archive › dc_af4c0c7fb720

SelfThinker: Self-Evolving Reasoning via Reliability-Verified Intrinsic Visual Thoughts — arXiv:2610.40115

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40115
License (as archived)
CC0-1.0
Archived
2026-11-01T02:42:18.339Z
SHA-256 of the archived text
a0de54315c5572f9fa5c3989ec042a4a77dd88703bff70e476cf96da194d992b
Stable URL of this page
https://metraipolis.com/documento/dc_af4c0c7fb720

How to cite

SelfThinker: Self-Evolving Reasoning via Reliability-Verified Intrinsic Visual Thoughts — arXiv:2610.40115 — arXiv (en), https://arxiv.org/abs/2610.40115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af4c0c7fb720 (Metraipolis archive dc_af4c0c7fb720, sha256 a0de54315c5572f9fa5c3989ec042a4a77dd88703bff70e476cf96da194d992b)
BibTeX
@misc{dcaf4c0c7fb720,
  title = {SelfThinker: Self-Evolving Reasoning via Reliability-Verified Intrinsic Visual Thoughts — arXiv:2610.40115},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40115},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af4c0c7fb720; sha256 a0de54315c5572f9fa5c3989ec042a4a77dd88703bff70e476cf96da194d992b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unified multimodal models can both generate and understand images within a single set of weights, offering an opportunity to use image synthesis as training supervision for visual comprehension. However, existing visual chain-of-thought methods rely on human-annotated helper images during training and require slow image generation at test time. We present SelfThinker, the first self-evolving framework that turns a unified model's self-generated visual thoughts into stronger understanding without human image annotations. Given a visual problem, SelfThinker samples candidate helper images from its generation pathway and uses its frozen understanding pathway to score each candidate via conditional pointwise mutual information. High-utility visual thoughts then refine the generator via flow matching and serve as privileged teacher context for on-policy self-distillation. At inference, SelfThinker reasons directly from the original image in text without generating intermediate images. Although trained only on small synthetic visual-search and navigation datasets, SelfThinker transfers broadly to natural-image and spatial benchmarks, raising the seven-benchmark average of ThinkMorph-7B from 52.7 to 64.0 (+11.3 points). Controlled image-perturbation probes further show that SelfThinker surpasses ThinkMorph-7B by up to 40.4 points and its pretrained BAGEL-7B backbone by up to 23.2 points across fine-grained and spatial perception tasks. Our code is available 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/2610.40115 — 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 2026-11-01T02:16:43.970Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).