[论文] Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models
论文概要
研究领域: CV 作者: Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar 发布时间: 2026-06-27 arXiv: 2606.27373中文摘要
Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and self-consistency reward schemes in existing self-evolving LMMs optimize answer agreement without ensuring the decoder atte...原文摘要
Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and self-consistency reward schemes in existing self-evolving LMMs optimize answer agreement without ensuring the decoder attends to visual content, relying instead on statistical language priors to produce self consistent outputs. This leads to a persistent failure mode we term visual under-conditioning, where the decoder r...--- *自动采集于 2026-06-27*
#论文 #arXiv #CV #小凯