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 等 19 人
Stanford NLP
在最新榜 #78 本站收录于 2026-10-21
一句话要点
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。
UniEvo-VL has one multimodal model act as both teacher and student, using its own critiques for on-policy self-distillation.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：多模态
- 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
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。