DriveLM : Driving with Graph Visual Question AnsweringChonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Jens Beißwenger, Ping Luo, Andreas Geiger, Hongyang LiECCV 24 -https://arxiv.org/abs/2312.14150 Summary 일반화 부족: 새로운 환경이나 센서 설정에 대한 적응력이 낮음.설명 가능성 부족: 유럽연합(EU) 등에서 요구하는 투명한 의사결정 과정을 제공하지 못함.단계별 사고 과정 결여: 인간 운전자는 **객체 인식(Perception) → 예측(Prediction) → 계획(Planning)**..

LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen | MSICLR 22 Contents1. ChatGPT    1-1. GPT-1     1-2. GPT-2     1-3. GPT-3    1-4. GPT-4    1-5. Instruct GPT - [https://jaeha-lee.tistory.com/91]    1-6. RLHF2. LLama 3. Gemini4. DeepSeek5. LLaVA    5-1. LLaVA - https://jaeha-lee.tistory.com..

Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023[https://arxiv.org/abs/2304.08485] Contents1. ChatGPT    1-1. GPT-1     1-2. GPT-2     1-3. GPT-3    1-4. GPT-4    1-5. Instruct GPT    1-6. RLHF2. LLama 3. Gemini4. DeepSeek5. LLaVA    5-1. LLaVA - https://jaeha-lee.tistory.com/93    5-2. LLaVA-Next    5-3. LLaVA-NeXT-Interleave6. LoRA  SummaryVisual Instruc..

LLMChatGPT PapersGPT-1 : Improving Language Understanding by Generative Pre-Training. - Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever [pdf] 2018.6GPT-2 : Language Models are Unsupervised Multitask Learners. - Alec Radford, Jeff Wu, Rewon Child, D. Luan, Dario Amodei, Ilya Sutskeve [pdf] 2019.2GPT-3 : Language Models are Few-Shot Learners. - Tom B. Brown, Benjamin Mann, Nick Ryde..

Improving Language Understanding by Generative Pre-TrainingInstructGPT - [2203.02155] Training language models to follow instructions with human feedback]Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, OpenAINeurIPS, 2022 - https://arxiv.org/abs/2203.02155 Contents1. ChatGPT    1-1. GPT-1     1-2. GPT-2     1-3. GPT-3    1-4. GPT-4    1-5. Instruct GPT - (Tr..