A curated reading list of ~50 foundational language modeling papers, each summarized in one witty sentence riffing on 'X is all you need.' Covers transformers (Attention, GPT, BERT, T5), scaling laws (Chinchilla, LLaMA), fine-tuning techniques (LoRA, QLoRA, InstructGPT, DPO), retrieval-augmented generation (RAG, DPR, HyDE), multimodal models (CLIP, ViT), and more. Intended as a starter kit for running a weekly ML paper club.
