CV & NLP 논문 리뷰
1.[논문 리뷰] VGG net
\[논문 리뷰] VGGnet(2014) 설명\[논문 리뷰] Very Deep Convolutional Networks for Large-Scale Image Recognition 리뷰, VGG NetBackgroundConvolutional Networks (ConvN
2.[논문 리뷰] Resnet - Deep Residual Learning for Image Recognition
📢 Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun1) 논문 베이스 세부 설명https://phil-baek.tistory.com/ent
3.[논문 리뷰] You Only Look Once : Unified, Real-Time object Detection(YOLO)
https://m.blog.naver.com/kisooofficial/223068590035YOLO 연구진은 객체 검출(object detection)에 새로운 접근방식을 적용.기존의 multi-task(classification) 문제를 하나의 회귀(regr
4.[논문리뷰]RCNN-Rich Feature hieerarchies for accurate object detection and semantic segmentation
Rich Feature hieerarchies for accurate object detection and semantic segmentation Author: Joseph Redmon∗, Santosh Divvala∗†, Ross Girshick¶, Ali Farh
5.[논문리뷰]AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE - VIT
Author: Alexey Dosovitskiy∗,†, Lucas Beyer∗, Alexander Kolesnikov∗, Dirk Weissenborn∗,Xiaohua Zhai∗ , Thomas Unterthiner, Mostafa Dehghani, Matthias M
6.[논문 리뷰] Bert : Pre-training of Deep Bidirectional Transformers for Language Understanding
Author: Jacob Devlin Ming-Wei Chang Kenton Lee Kristina ToutanovaPublished Date: 2019년 3월 1일keyword: Vit, attentionstatus: not yet스터디 주제: 주제: BERT 모델의
7.[nlp][논문리뷰]Parameter-Efficient Transfer Learning for NLP
\[논문 리뷰] Parameter-Efficient Transfer Learning for NLP (Adapter)GPT와 BERT와 같은 대형 언어 모델(LLM)을 fine-tuning하는 것은 매우 효과적인 전이 메커니즘(transfer mechanism)이다. 그
8.[nlp][논문리뷰] Improving Language Understanding by Generative Pre-Training
\[논문리뷰] GPT-1(Improving Language Understandingby Generative Pre-Training)의 이해GPT-1 논문 리뷰 - ChatGPT의 근간이 되는 논문 완벽하게 이해하기\[GPT-1 논문 리뷰] - Improving Lang
9.[nlp][논문 리뷰] BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
status: Finished!스터디 주제: 주제: BART 응용 및 실습논문: • BART 모델 구조 및 특징 이해• denoising 기법의 적용방법 및 효과• time step 별 이해 (croos attention > encoer > decode
10.[nlp][논문리뷰] Instructive GPT (업데이트 예정 : APPENDIX 내용 추가 분석 필요!)
status: Finished!스터디 주제: 주제 : Instructive GPT1\. 논문에서 이해하면 좋을 포인트• Instruct GPT 등장 배경 ◦ 인간의 의도(Human Feedback)을 반영하고자 하게 된 계기: 크게 Untruthful, Toxic
11.[nlp][논문리뷰] Parameter-Efficient Transfer Learning for NLP
https://miniature-textbook-570.notion.site/Parameter-Efficient-Transfer-Learning-for-NLP-6-1318da87b70881c0b53ed1b9fe3fdf88?pvs=4\[논문 리뷰] Paramet
12.[nlp][논문리뷰] LORA: LOW-RANK ADAPTATION OF LARGE LAN- GUAGE MODELS
https://miniature-textbook-570.notion.site/LORA-LOW-RANK-ADAPTATION-OF-LARGE-LAN-GUAGE-MODELS-7-1318da87b708811eb4f7cf1d769991f1?pvs=4\[LoRA 논문 리
13.[nlp][논문리뷰]QLoRA: Efficient Finetuning of Quantized LLMs - 8주차
https://miniature-textbook-570.notion.site/QLoRA-Efficient-Finetuning-of-Quantized-LLMs-8-1398da87b7088097b23def7b62a90a2b?pvs=4\[QLoRA] QLoRA: E
14.[nlp][논문리뷰] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks - 9주차
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\[논문리뷰] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\[논문 리뷰] Retri