VLM_Newbie·Oct 20[RAG] DPR: Dense Passage Retrieval for Open-Domain QA논문: Karpukhin et al. 2020, arXiv:2004.04906 (EMNLP 2020)
VLM_Newbie·Oct 19[RAG] RAG의 뿌리를 찾아서: 2020년 BART+DPR의 ‘수학적 접근’부터 현대 LLM 기반 In-Context RAG까지AI 엔지니어라면 누구나 매일같이 다루는 RAG (Retrieval-Augmented Generation).
VLM_Newbie·Aug 8[NeurIPS 2025]Think or Not?Jiaqi Wang, Kevin Qinghong Lin, James Cheng, Mike Zheng Shou
VLM_Newbie·Jun 17LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding기존 연구의 한계 (Problem Statement)
VLM_Newbie·May 11Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language ModelsAbstract
VLM_Newbie·Apr 8Caching Strategies for VLM Inference: vLLM APC vs LangChain CacheWhen deploying Vision Language Models (VLMs) in production, it’s common to encounter repeated or similar image+prompt combinations…
VLM_Newbie·Apr 6[NeurIPS ‘25] Perception Encoder: The best visual embeddings are not at the output of the networkPerception Encoder: 가장 훌륭한 시각 임베딩은 네트워크의 출력층에 있지 않다
VLM_Newbie·Feb 11[arXiv2504]VLM-R1: A Stable and Generalizable R1-style Large Vision-Language ModelVLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
VLM_Newbie·Nov 17, 2025[VLM] InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal…InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models