arXiv 2609.38721 · cs.AI · 2026-09-30
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Fang Wu, Da Xing, Yanjie Huang, Junxi Wang, Ji Wang, Hejia Geng, Guancheng Wan, Bowen Zuo and 11 more
Stanford NLP
In latest · #78 Added on 2026-10-21
One-line takeaway
UniEvo-VL has one multimodal model act as both teacher and student, using its own critiques for on-policy self-distillation.
UniEvo-VL 让同一个多模态模型分别扮演教师和学生，用自我批评做在线自蒸馏实现自我提升。
Read on arXiv PDF Hugging Face discussion
Topics & disciplines
More on Multimodal
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲560
- LoopVL: Recurrent Visual Intelligence ▲417
- VideoJev: System One Model for Video Understanding and Interaction ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models ▲270
- OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction ▲238
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.