[논문리뷰] Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMsJingyi Liao이 arXiv에 게시한 'Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs' 논문에 대한 자세한 리뷰입니다.#Review#Multimodal Large Language Models (MLLMs)#Visual Reference Tokens (VRTs)#Dense Prediction#Referring Expression Comprehension (REC)#Open-Vocabulary Detection (OVD)#Image Captioning#Unified Architecture#Autoregressive Generation2025년 10월 9일댓글 수 로딩 중