Metraipolis › archive › dc_f7acac73b87d
Distilling Visual Reasoning into Text Space — arXiv:2609.34408
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34408
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:52:07.928Z
- SHA-256 of the archived text
b5a7a615795019c7f5fadc9f4994c6c0dba581e4274726400a6636eaef0c5461- Stable URL of this page
https://metraipolis.com/documento/dc_f7acac73b87d
How to cite
Distilling Visual Reasoning into Text Space — arXiv:2609.34408 — arXiv (en), https://arxiv.org/abs/2609.34408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f7acac73b87d (Metraipolis archive dc_f7acac73b87d, sha256 b5a7a615795019c7f5fadc9f4994c6c0dba581e4274726400a6636eaef0c5461)
BibTeX
@misc{dcf7acac73b87d,
title = {Distilling Visual Reasoning into Text Space — arXiv:2609.34408},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34408},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f7acac73b87d; sha256 b5a7a615795019c7f5fadc9f4994c6c0dba581e4274726400a6636eaef0c5461},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Vision-Language Models (LVLMs) have shown strong promise for multimodal reasoning, yet often struggle with tasks requiring concepts beyond what is directly observable in the input image. Existing methods generate intermediate images or latent visual tokens to guide reasoning, but these representations can introduce errors and increasingly interfere with textual reasoning as reasoning progresses. We propose Visual-to-Text Chain-of-Thought Distillation (V2T), a framework that enables LVLMs to internalize visual reasoning without generating intermediate visual representations at inference time. V2T first trains a teacher LVLM using interleaved visual and textual chains of thought, and then uses knowledge distillation to train a student LVLM using the teacher's logits and cross-entropy supervision from ground-truth textual reasoning. When reasoning images can be mapped to the original image, V2T can additionally distill the teacher's attention to corresponding regions, while ground-truth bounding boxes can further guide a subsequent reinforcement learning stage. Experiments across multiple multimodal reasoning benchmarks show that V2T consistently outperforms the teacher and existing baselines, improving average accuracy by 14.3% on a held-out set and 2.7% on the broader visual evaluation suite. Moreover, lightweight SFT and substantially reduced RL make V2T up to 42x faster to train than state-of-the-art baselines. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34408 — 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 2026-10-07T23:29:27.367Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).