• KAIST IC Lab Intern, KAIST IC Lab / 2024.07 ~
• Alethio ML Researcher Intern, Alethio Co., Ltd. / 2023.08 ~ 2023.12
• LG Aimers 3th, LG Aimers / 2023.07 ~ 2023.09
• NLP AI Developer 5th, BoostCamp AI Tech / 2023.03 ~ 2023.08
• Hansung University Undergraduate Researcher : Visual Intelligence Lab. / 2023.03 ~ 2023.04
• Hansung University Undergraduate Researcher : Marusys edu Co., Ltd. / 2022.06 ~ 2023.03

• Hansung University - Hansung Bllossom GPT Serving, Demo / 2024.05. ~ 2024.06.
• Visualize Diffusion Cross Attention Map for Text-to-Image, Demo / 2023.10. ~ 2023.12.
• Boostcamp AI Tech - LawBot(Legal-GPT) Project Serving, Final Project / 2023.07. ~ 2023.08.
• Boostcamp AI Tech - Open-Domain Question Answering, ODQA / 2023.06.07 ~ 2023.06.22
• Boostcamp AI Tech - Topic Classification, TC / 2023.05.24 ~ 2023.06.01
• Boostcamp AI Tech - Relation Extraction, RE / 2023.05.03 ~ 2023.05.18
• 2023년 K-디지털 트레이닝 해커톤 예선 진출 / 2023.05.17
• Boostcamp AI Tech - Semantic Text Similarity, STS / 2023.04.12 ~ 2023.04.20
• Visual Intelligence Lab, Food Object Detection Project / 2023.03. ~ 2023.04.
• 2023 교원그룹 AI 챌린지 본선 진출, Dacon / 2023.01.30 ~ 2023.02.13
• TV 손 동작 제어 비디오 인식 AI 경진대회, Dacon / 2023.01.02 ~ 2023.02.06
• 2022 국방 AI 경진대회 본선 진출, AI Connect / 2022-09-30 ~ 2022-12-01
• Marusys edu Co., Ltd. 유아용 AI TeachableMachine 개발, Marusys edu Co., Ltd. / 2022-06. ~ 2023-03.

• kfkas/Hansung-Llama-3-8B / Huggingface
• kfkas/Legal-Llama-2-ko-7b-Chat⚖️🦙 / Huggingface
• YoonSeul/LawBot-level-3-KuLLM-5.8B-tae-2epoch⚖️ / Huggingface
• kfkas/Llama-2-ko-7b-Chat🦙 / Huggingface
• kfkas/legal-question-filter-koelectra / Huggingface
• kfkas/t5-large-korean-P2G / Huggingface
• kfkas/t5-large-korean-news-title-klue-ynat / Huggingface
• kfkas/RoBERTa-large-Detection-G2P / Huggingface

🎉kfkas/Llama-2-ko-7b-Chat🦙 모델이 51k 다운로드를 돌파하였습니다.🎉

• SLIP: Self-supervision meets Language-Image Pre-training / SLIP
• BEiT: BERT Pre-Training of Image Transformers / BEiT
• FINE-GRAINED INTERACTIVE LANGUAGE- IMAGE PRE-TRAINING / FILIP
• Align before Fuse: Vision and Language Representation Learning with Momentum Distillation / ALBEF
• Visual Instruction Tuning / LLaVA
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text / VATT
• One Embedding Space To Bind Them ALL / ImageBind
• HyperNetworks for Fast Personalization of Text-to-Image Models / HyperDreambooth
• A Successor to Transformer for Large Language Models / RetNet
• Language Models are Unsupervised Multitask Learners / GPT-2
• Learning Transferable Visual Models From Natural Language Supervision / CLIP
• Improving Language Understanding by Generative Pre-Training / GPT-1
• Pre-training of Deep Bidirectional Transformers for Language Understanding / BERT
• Attention is all you need / Transformer
• Effective Approaches to Attention-based Neural Machine Translation / Seq2Seq with Attention
• Sequence to Sequence Learning with Neural Networks / Seq2Seq
• TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models / TrOCR
• SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers / Segformer
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale / Vision Transformer
• Involution: Inverting the Inherence of Convolution for Visual Recognition / Involution
• Micro-Batch Training with Batch-Channel Normalization and Weight Standardization / Weight Standardization
• Big Transfer (BiT): General Visual Representation Learning / BiT

일부 리뷰는 Youtube, Velog에서 확인할 수 있습니다.

Baekjoon Tier