Physics of Language Models_ Part 2.1, Grade-School Math and the Hidden Reasoning
ICML 2024 Tutorial_ Physics of Language Models
Physics of Language Models_ Part 3.1 + 3.2, Knowledge Storage, Extraction and Ma
Physics of Language Models_ Part 1, Context-Free Grammar after
Audio Language Models - Neil Zeghidour (Moshi)
第四讲：Transformer 的时代要结束了吗？介紹 Transformer 的竞争者们
吴恩达《自然语言处理|natural language processing》中英字幕
The KV Cache: Memory Usage in Transformers
【清华大学】Transformer从入门到精通，全程干货无废话！让你少走99%的弯路！（原理+模型搭建+注意力机制+实战+代码讲解）
第五讲：大型语言模型训练方法「预训练–对齐」(Pretrain-Alignment) 的强大与极限
Future Directions in Neural Speech Communication Codecs - Minje Kim (UIUC)
DPO V.S. RLHF 模型微调
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
VoiceCraft Zero-Shot Speech Editing and TTS in the Wild - Shang-Wen Li (Meta)
Jeff Dean s talk at ETH Zurich in April 2025 on important trends in AI
第16讲：可以加速所有语言模型生成速度的神奇外挂— Speculative Decoding
8篇scaling laws 论文泛读，哪篇是你的心头好？Scaling Law
Challenges in Developing Universal Audio Foundation Model - Dongchao Yang (CUHK)
第18讲：有关影像的生成式AI (下) — 快速导读经典影像生成方法 (VAE, Flow, Diffusion, GAN)
【B站最全】吴恩达详解大模型中的Langchain+RAG+Transformer工作原理，小白教程，全程干货无尿点，学完你就是AGI的大佬！（附课件+代码）
