Metraipolis › archive › dc_fd42d27784dd
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement — arXiv:2608.03733
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03733
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:16:37.185Z
- SHA-256 of the archived text
18e094822e7452cbe2b79d2292135065cd43f9a564484ee0e119063d1c691ff0- Stable URL of this page
https://metraipolis.com/documento/dc_fd42d27784dd
How to cite
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement — arXiv:2608.03733 — arXiv (en), https://arxiv.org/abs/2608.03733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd42d27784dd (Metraipolis archive dc_fd42d27784dd, sha256 18e094822e7452cbe2b79d2292135065cd43f9a564484ee0e119063d1c691ff0)
BibTeX
@misc{dcfd42d27784dd,
title = {Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement — arXiv:2608.03733},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03733},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd42d27784dd; sha256 18e094822e7452cbe2b79d2292135065cd43f9a564484ee0e119063d1c691ff0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision. However, existing MLLM self-augmentation methods are largely text-centric, while image augmentation remains underexplored and typically relies on generic or handcrafted transformations that are weakly aligned with the model's actual incapability. We propose Failure-informed Image Self-Augmentation (\textbf{FISA}), a framework for MLLM self-improvement that constructs augmented images from the model's own failure cases. Our method generates visually challenging yet answer-preserving image complications, verifies their utility through self-examination, and applies dual fidelity filtering to avoid semantic distortion. Experiments on visual question answering benchmarks show that the proposed method consistently improves performance across both in-distribution and out-of-distribution settings. Further experiments validate the compatibility of FISA with existing textual self-augmentation approaches, the superior data efficiency of the synthesized samples over generic image augmentation baselines, and the practical effectiveness of the proposed filtering strategy.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03733 — 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 2026-10-31T12:05:52.843Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).