Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation 文章

ArXiv CS.CV2026-05-27NEWSen作者: Joseph Hoche, David Brellmann, Gianni Franchi

大语言模型

查看原文 →

Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation · 相关技术

相关技术

ODE language model Vision Language Models Token Tera ORM Large vision-language model VLM LVLMs LMM ICT HIS Gin For Effort Metric Attention DAPT ARG ANN AGI