时间: 2023.6.26-2023.7.2
最新技术:
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
论文:arxiv.org
Extending Context Window of Large Language Models via Positional Interpolation
论文:arxiv.org
Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language
论文:arxiv.org
ViNT: A Foundation Model for Visual Navigation
论文:arxiv.org
Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
论文:arxiv.org
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
论文:arxiv.org
Long-range Language Modeling with Self-retrieval
论文:arxiv.org
Understanding Social Reasoning in Language Models with Language Models
论文:arxiv.org
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
论文:arxiv.org
Scaling MLPs: A Tale of Inductive Bias
论文:arxiv.org
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
论文:arxiv.org
DreamDiffusion: Generating High-Quality Images from Brain EEG Signals
论文:arxiv.org
Generate Anything Anywhere in Any Scene
论文:arxiv.org
MotionGPT: Human Motion as a Foreign Language
论文:arxiv.org
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
论文:arxiv.org
Instruction Tuning 阶段性总结
OpenAI独家绝技也被开源超越啦?!DPO让小白轻松玩转RLHF!
课程:
LLM Learning Lab
LLM in Production
商业:
The Rise of the AI Engineer
Inflection-1: Pi’s Best-in-Class LLM
62人大模型公司卖了93亿元!AIGC最大收购案诞生:华人联创,两年估值翻6倍
案例:
快捷部署清华大模型 ChatGLM2-6B,一键搞定 HuggingFace Space 空间
QLoRA + 百万数据,多卡高效微调 BLOOM-7b1 模型
使用 Transformers 为多语种语音识别任务微调 Whisper 模型
开源中英教育对话大模型