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

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

在常规推荐系统算法和系统双优化的范式下，一线公司针对单个任务或单个业务的效果挖掘几乎达到极限。从2019年我们开始关注多种信息的萃取融合，提出了OneRec算法，希望通过平台或外部各种各样的信息来进行知识集成，打破数据孤岛，极大扩充推荐的“Extra World Knowledge”。 已实践的算法包括行为数据，内容描述，社交信息，知识图谱等。在OneRec，每种信息和整体算法的集成是可插拔…

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

Best Practices on Recommendation Systems

🔨 跨域序列推荐（Cross-Domain Sequential Recommendation）的算法工具箱，旨在提供序列推荐、跨域推荐、跨域序列方法的baseline实现。目前本工具箱已包括TiSASRec、CoNet、PINet、MIFN这四种方法的实现。

Source code for NoteLLM and NoteLLM-2

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

A framework for large scale recommendation algorithms.

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

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

A PyTorch implementation of Ranking Distillation

DE-RRD: A Knowledge Distillation Framework for Recommender System (CIKM'20)

[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"

SASRec: Self-Attentive Sequential Recommendation

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

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

Versatile End-to-End Recommender System

A Comparative Framework for Multimodal Recommender Systems

MLGB is a library that includes many models of CTR Prediction & Recommender System by TensorFlow & PyTorch. 「妙计包」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。

I have surveyed the technology and papers of CTR & Recommender System, and implemented 25 common-used models with Pytorch for reusage. （对工业界学术界的CTR推荐调研并实现25个算法模型，2023）