InterviewReady/ai-engineering-resources
Research papers and blogs to transition to AI Engineering
### Overview:
This repository is a curated collection of research papers and blogs aimed at helping software engineers transition into the field of AI engineering. It covers various aspects of AI, including tokenization, vectorization, infrastructure, core architecture, mixture of experts, reinforcement learning with human feedback, chain of thought, reasoning, optimizations, and distillation. The goal is to provide a comprehensive understanding of AI engineering principles and techniques.
### Key features:
- **Tokenization**: Papers on Byte-pair Encoding, Byte Latent Transformer, BERT, and others.
- **Vectorization**: Papers on BERT, IMAGEBIND, SONAR, FAISS, and Milvus.
- **Infrastructure**: Papers on TensorFlow, Deepseek filesystem, Milvus DB, and FAISS.
- **Core Architecture**: Papers on Attention, FlashAttention, Multi Query Attention, Grouped Query Attention, and Google Titans.
- **Mixture of Experts**: Papers on Sparsely-Gated Mixture-of-Experts Layer, GShard, and Switch Transformers.
- **RLHF**: Papers on Deep Reinforcement Learning with Human Feedback and Fine-Tuning Language Models with RHLF.
- **Chain of Thought**: Papers on Chain-of-Thought Prompting, Chain of thought, and Demystifying Long Chain-of-Thought Reasoning in LLMs.
- **Reasoning**: Papers on Transformer Reasoning Capabilities, Large Language Monkeys, Scaling Inference Compute with Repeated Sampling, and Training Large Language Models to Reason in a Continuous Latent Space.
- **Optimizations**: Papers on The Era