This blog currenlty contains a total of 246 posts : 116 (AI), 61 (Code), 29 (Util), and 40 (Note). I am excited to launch my new blog. I believe that this personal website make an opportunity to disseminate my academic endeavors with the world. …
Read moreFeatured Post
[VLM] Vision Language Models 3
๐ Analysis of VLMs / Understanding VLMs ◽️ What matters when building vision-language models? Hugging face, arXiv, 2024. Intr…
[VLM] Vision Language Models 2
๐ Vision-centric Improvement / Region-based VLMs / Hallucination ◽️ Eyes Wide Shut? Exploring the Visual Shortcomings of Multim…
[VLM] Vision Language Models 1
๐ Vision Laungague Model ◽️ Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks ECCV20 Problem: Existi…
[VLM] Paper list
General VLM (BLIP2 > BLIP = OSCAR(detector-based) = SimVLM = LEMON(Scaling up vision-language pre-training for image captio…
[Note] Hot papers in April 2024
240425_Trend A. Retrieval augmented generation (RAG) Architecture What is RAG? ( LinkedIn ) How RAG works? In terms of L…
Most Popular
[VLM] Paper list
General VLM (BLIP2 > BLIP = OSCAR(detector-based) = SimVLM = LEMON(Scaling up vision-language pre-training for image captio…
[Pytorch ์ค์ต] AutoEncoder๋ฅผ ์ฌ์ฉํ, Fashion Mnist data๋ฅผ ํ์ฉ
Fashion MNIST train, test ๋ฐ์ดํฐ์ ์ ๋ฏธ๋ฆฌ ๋ค์ด๋ก๋ ํ ํ์ ์์. PS. jupyter ์คํ๊ฒฐ๊ณผ๋ ์ฝ๋ ๋ฐ์ค๋ก ์ถ๋ ฅ๋์ด ์์ต๋๋ค. matplot์ ์ด์ฉํด์ ์ด๋ฏธ์ง๋ฅผ ์ถ๋ ฅํ๋ ์ด๋ฏธ์ง๋ ์ฒจ๋ถํ์ง ์์์ต๋๋ค.…