作者位次 #4/8ICML 2026Poster· Deep Learning / Large Language Models
Do Vision and Text Cues Exhibit Evidential Coupling? UFO: A Benchmark for Compositional Multimodal Reasoning in Unified Models
Zhongyu Yang · Dannong Xu · Yonghan Zhang · Kefan Chen · Xinyi Wang · Yang Xu · Wei Pang · Yingfang Yuan