This repository is a curated list of influential deep learning papers relevant to industrial search, recommendation, and advertising systems. It serves as a valuable resource for researchers and engineers seeking to understand and implement state-of-the-art techniques in areas like embedding, matching, ranking, and large-scale models.

How It Works

The repository organizes papers by key functional areas within recommendation systems (e.g., Embedding, Matching, Ranking, LLM). Each entry typically includes the paper's title, publication venue and year, and a brief identifier (e.g., [Word2vec]). This structured approach allows users to quickly navigate and identify foundational or recent advancements in specific sub-fields.

Quick Start & Requirements

This repository is a collection of academic papers and does not require installation or execution. It serves as a reference guide.

Highlighted Details

• Comprehensive coverage across core recommendation system components: Embedding, Matching, Ranking, Post-Ranking, LLMs, Transfer Learning, Reinforcement Learning, and more.
• Extensive inclusion of papers from major tech companies (Google, Alibaba, Meta, Amazon, Microsoft, etc.) and top-tier conferences (KDD, NIPS, ICLR, WWW, SIGIR, etc.).
• Categorization includes foundational techniques (e.g., Word2vec, Wide & Deep) and cutting-edge research (e.g., LLM-based retrieval, generative recommendations).

Maintenance & Community

The repository is maintained by guyulongcs. Further community engagement details are not specified in the README.

Licensing & Compatibility

The repository itself is a list of links to academic papers. The licensing of the papers themselves varies by their original publication. Compatibility for commercial use depends on the individual papers' copyrights and licenses.

Limitations & Caveats

This is a curated list of papers, not an implementable codebase. It does not provide code, implementations, or direct access to the models discussed. Users must locate and implement the papers themselves.