Papers

This repo contains notes and highlights on scientific papers that I read.

Highlighting Color Meanings:

- the most important concepts.

- tough and meaningfull.

- illustrative examples.

Big Data

Tags	Highlights	Title	Year	Link
DNP	MapReduce	MapReduce: Simplified Data Processing on Large Clusters	2004	research.google

Computer Vision

Tags	Highlights	Title	Year	Link
Segmentation	U-Net	U-Net: Convolutional Networks for Biomedical Image Segmentation	2015	arxiv

Natural Language Processing

Tags	Highlights	Title	Year	Link
cIE	ReLiK	ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget	2024	arxiv
Embeddings	Word2Vec 1	Efficient Estimation of Word Representations in Vector Space	2013	arxiv
	Word2Vec 2	Distributed Representations of Words and Phrases and their Compositionality	2013	arxiv
	GloVe	GloVe: Global Vectors for Word Representation	2014	aclanthology
LLM	Transformer	Attention Is All You Need	2017	arxiv
	DeepSeek-R1	DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning	2025	github
RAG	RAG4NLP	Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks	2020	arxiv

Reinforcement Learning

Tags	Highlights	Title	Year	Link
Go game	AlphaGo Lee	Mastering the game of Go with deep neural networks and tree search	2016	nature
	AlphaGo Zero	Mastering the game of Go without human knowledge	2017	nature

Interpretability

Tags	Highlights	Title	Year	Link
Global	SHAP	A Unified Approach to Interpreting Model Predictions	2017	arxiv
Global	TCAV	Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)	2017	arxiv
Loss	Harmonic Loss	Harmonic Loss Trains Interpretable AI Models	2025	arxiv

Domain Specific

Tags	Highlights	Title	Year	Link
People	Life2Vec	Using sequences of life-events to predict human lives	2023	nature

---

Glossary

• DNP - Distributed and Network Programming
• cIE - closed Information Extraction
• LLM - Large Language Model
• RAG - Retrieval Augmented Generation