UniEvo-VL: マルチモーダルモデルの自己改善のための自己蒸留トレーニング
UniEvo-VL: Self-Distillation Training for Multimodal Model Self-Improvement (arxiv.org)
要約
UniEvo-VLは、マルチモーダルモデルがテスト時の計算中に自身の建設的な自己修正フィードバックから学習するための自己進化フレームワークです。外部の教師モデルに頼るのではなく、モデル自身の自己批評を特権情報として活用し、単一のマルチモーダルモデルが異なるコンテキストで教師と生徒の両方として機能します。この手法は、画像生成能力を向上させ、追加の反射情報への感度を維持することが実験で示されています。
全文翻訳
Computer Science > Artificial Intelligence
arXiv:2609.38721 (cs)
[Submitted on 30 Sep 2026]
Title: UniEvo-VL: マルチモーダルモデルの自己改善のためのオンポリシー自己蒸留トレーニングレシピ
Authors: Fang Wu, Da Xing, Yanjie Huang, Junxi Wang, Ji Wang, Hejia Geng, Guancheng Wan, Bowen Zuo, Xiaomin Li, Shixiang Tang, Xinyu Xiang, Zehong Wang, Shiyi Du, Peng Xia, Shuangjia Zheng, Yining Hong, Li Erran Li, Jure Leskovec, Yejin Choi
View a PDF of the paper titled UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement, by Fang Wu and 18 other authors
Abstract: Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback during test-time compute. Instead of relying on a separate, often larger, teacher, we leverage their self-critiques as privileged information and ask a single multimodal model to act as both teacher and student with different contexts. The student only sees the vanilla question, while the teacher conditions on the privileged critique. Then training minimizes the per-state divergence between their denoising diffusion distributions over the student's own sampling trajectories. Experiments demonstrate that UniEvo-VL improves the image generation capabilities of multimodal models, while maintaining their sensitivity to additional reflection information. Specifically, we build on top of the open-source Qwen-image-2512 and observe a significant performance gain from 0.747 to 0.808 on GenEval and from 32.97 to 35.53 on GenEval2 Soft-TIFA. Moreover, attempts with more powerful external critics (e.g., GPT5.6-Luna) show that multimodal models with strong judge capabilities can anticipate a higher self-evolving ceiling. Last but not least, mixed text-rendering outcomes show that our self-improvements may not be uniform across different tasks. Our study aims to shed light on the current hot recursive self-improvement research line to enhance the user experience when using multimodal models without external supervision or guidance.
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2609.38721 [cs.AI] |
| (or arXiv:2609.38721v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38721 arXiv-issued DOI via DataCite |
Submission history
From: Fang Wu [view email]
[v1] Wed, 30 Sep 2026 00:54:09 UTC (42,272 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement, by Fang Wu and 18 other authors
[画像: license icon] view license
Additional Features
Current browse context:
cs.AI
Change to browse by:
References & Citations
Loading...
BibTeX formatted citation
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
- Author
- Venue
- Institution
- Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)