Skip to content
星际流动

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

发布
采集
学术前沿 5.4 分 — 中等质量:常规学术论文,有适度参考价值
原文: cs.AI updates on arXiv.org

评分 5.4 · 来源:cs.AI updates on arXiv.org · 发布于 2026-04-14

评分依据:中等质量:常规学术论文,有适度参考价值

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

arXiv:2604.10949v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, however, this synergy remains elusive: UMMs fail to transfer LLM-like reasoning to image synthesis and exhibit divergent response behaviors. We term this phenomenon pseudo-unification. Diagnosing its internal causes is important, but existing probing methods either lack…