Back to Home

Resources

Important papers I have read and GitHub repos which contain code implementations.

Papers

Attention is All You NeedPaper

The foundational 2017 paper by Vaswani et al. that introduced the Transformer architecture.

Neural Machine Translation by Jointly Learning to Align and TranslatePaper

Bahdanau et al. (2015) - The paper that introduced attention mechanisms to seq2seq models.

Effective Approaches to Attention-based Neural Machine TranslationPaper

Luong et al. (2015) - Introduced global and local attention variants for improved efficiency.

Distilling the Knowledge in a Neural NetworkPaper

Hinton et al. (2015) - Introduces knowledge distillation, showing how a smaller student model can be trained to mimic a larger teacher model using soft probability targets.

Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsPaper

Wei et al. (2022) - Demonstrates that prompting LLMs with intermediate reasoning steps significantly improves performance on complex reasoning tasks.

Tutorials & Code

The Annotated TransformerTutorial

Harvard NLP's line-by-line implementation guide with detailed explanations and code.

Deep Learning ImplementationCode

PyTorch implementations of all architectures covered in the Foundations series.