Berkeley AI Research(@berkeley_ai)
Congratulations to BAIR Researchers from @trevordarrell lab whose paper "Hidden in plain sight: VLMs...
5.5内容质量
TL;DR · AI 摘要
BAIR团队论文指出视觉语言模型（VLMs）忽视自身视觉表征，获COLM2025杰出论文奖。
核心要点
- VLMs在推理中未充分利用其内部视觉表征
- 该问题被系统性发现并验证，具基础性意义
- 研究获COLM2025会议杰出论文奖认可
#视觉语言模型#VLM#AI研究#COLM2025
打开原文@xkungfu @tylerraye @databoydg" / X
Congratulations to BAIR Researchers from
lab whose paper "Hidden in plain sight: VLMs overlook their visual representations," was awarded an Outstanding Paper Award at #COLM2025 this week in Montreal, Canada.
Quote
Conference on Language Modeling
@COLM_conf
Oct 7, 2025
Replying to @COLM_conf
Outstanding paper 4
: Hidden in plain sight: VLMs overlook their visual representations openreview.net/forum?id=qQb1J
