Behavioral tests and SAE probing on 83 bistable images show simultaneous vision-tower activation of both aspects in 72% of cases, with causal steering succeeding on default-dominant but not force-balanced stimuli, locating the commitment bottleneck downstream of the vision tower.
arXiv preprint arXiv:2405.03207 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
League of LLMs organizes LLMs into a self-governed mutual evaluation league using dynamic, transparent, objective, and professional criteria to distinguish model capabilities with 70.7% top-k ranking stability.
citing papers explorer
-
Vision-Language Asymmetry in Bistable Image Captioning
Behavioral tests and SAE probing on 83 bistable images show simultaneous vision-tower activation of both aspects in 72% of cases, with causal steering succeeding on default-dominant but not force-balanced stimuli, locating the commitment bottleneck downstream of the vision tower.
-
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
League of LLMs organizes LLMs into a self-governed mutual evaluation league using dynamic, transparent, objective, and professional criteria to distinguish model capabilities with 70.7% top-k ranking stability.