/ Papershelf
Papers I've read
Research papers that shaped how I build — each with the one idea I took away from it.
- Dynamo: Amazon's Highly Available Key-value Store
- In Search of an Understandable Consensus Algorithm (Raft)
- Attention Is All You Need
- Efficient Memory Management for LLM Serving with PagedAttention
- QLoRA: Efficient Finetuning of Quantized LLMs
- LoRA: Low-Rank Adaptation of Large Language Models
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- ReAct: Synergizing Reasoning and Acting in Language Models
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines