Metraipolis › archive › dc_ea811f958fc2
Tiny Evidence Region Localization with Selective Contrastive On-Policy Self-Distillation — arXiv:2611.10734
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10734
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:42:44.011Z
- SHA-256 of the archived text
ab369e182aa1a2e7d89e29a1c6abdf2705424fe2321388d816dfd6ccbaca017f- Stable URL of this page
https://metraipolis.com/documento/dc_ea811f958fc2
How to cite
Tiny Evidence Region Localization with Selective Contrastive On-Policy Self-Distillation — arXiv:2611.10734 — arXiv (en), https://arxiv.org/abs/2611.10734 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea811f958fc2 (Metraipolis archive dc_ea811f958fc2, sha256 ab369e182aa1a2e7d89e29a1c6abdf2705424fe2321388d816dfd6ccbaca017f)
BibTeX
@misc{dcea811f958fc2,
title = {Tiny Evidence Region Localization with Selective Contrastive On-Policy Self-Distillation — arXiv:2611.10734},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10734},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea811f958fc2; sha256 ab369e182aa1a2e7d89e29a1c6abdf2705424fe2321388d816dfd6ccbaca017f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10734. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal large language models have made progress in general visual tasks. However, limitations remain in fine-grained visual tasks requiring evidence from minute image regions. Existing methods primarily train models using evidence-related regions while overlooking the influence of extensive background regions, resulting in a limited ability to resist interference from irrelevant regions. We propose selective positive-negative on-policy self-distillation (SPN-OPSD), which considers both evidence and background regions. Supervision from both views improves the model's ability to resist interference from irrelevant regions. Furthermore, selective token-level distillation provides more informative supervision, improving the model's ability to attend to evidence regions in Fine-Grained Visual Tasks. On Qwen3.5-2B, SPN-OPSD improves accuracy on V* Bench, ZoomBench, and MME-RealWorld-Lite from 76.44%, 45.92%, and 57.43% to 84.82%, 54.56%, and 59.56%, respectively. Similar gains are also observed on Qwen3.5-0.8B. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.10734 — 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 2026-11-10T18:37:37.601Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).