1
Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models
多模态大模型能否像人类一样评判美？这项研究系统评估了MLLM在开放式审美推理上的真实表现与局限。
arXiv:2606.29689v1 Announce Type: new Abstract: Open-ended aesthetic critique is a challenge for multimodal large language models (MLLMs): unlike mult…