作者位次 #2/7ACL 2026Findings· Findings of ACL
Can MLLM s Reason Beyond Language? V is R eason: A Comprehensive Benchmark for Vision-Centric Reasoning
Longteng Guo · Yifan Wang · Pengkang Huo · Tailai Chen · Yuze Wu · Jing Liu · Xinxin Zhu
摘要
Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce VisReason, a benchmark for vision-centric reasoning in everyday s...