"Exploring Scaling Laws of CTR Model for Online Performance Improvement." In Proceedings of RecSys '25.

This repository provides the code for implementing RPG described in our KDD'25 paper "Generating Long Semantic IDs in Parallel for Recommendation".

Vector (and Scalar) Quantization, in Pytorch

[KDD'25] LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation.

Train a 1B LLM with 1T tokens from scratch by personal

Best Practices on Recommendation Systems

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

Source code for NoteLLM and NoteLLM-2

HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling

Retrieval and Retrieval-augmented LLMs

[NeurIPS'24] The official implementation code of LLM-ESR.

A Comparative Framework for Multimodal Recommender Systems

Replication of the paper "Text Is All You Need: Learning Language Representations for Sequential Recommendation" on KDD'23.

A Toolbox for MultiModal Recommendation. Integrating 10+ Models...

MLGB is a library that includes many models of CTR Prediction & Recommender System by TensorFlow & PyTorch. MLGB是一个包含50+点击率预估和推荐系统深度模型的、通过TensorFlow和PyTorch撰写的库。

Code of Paper "ReLLa: Retrieval-enhanced Large Language Models for Mitigating Long Context Problems in Recommendation".

Versatile End-to-End Recommender System

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

Awesome Deep Learning papers for industrial Search, Recommendation and Advertising. They focus on Embedding, Matching, Ranking (CTR and CVR prediction), Post Ranking, Multi-task Learning, Graph Neu…

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

OpenAgents: An Open Platform for Language Agents in the Wild

Code for I3 Retriever, accepted by CIKM'23.

TensorFlow implementation of Adaptive Information Transfer Multi-task (AITM) framework. Code for the paper accepted by KDD21: Modeling the Sequential Dependence among Audience Multi-step Conversion…

Source code of CIKM 2022 and DLP-KDD workshop 2022 Best Paper: IntTower-“ IntTower: the Next Generation of Two-Tower Model for Pre-ranking System”