"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

The Official implementation of our paper "RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment"

Office codebase for ICML 2025 paper "Core Knowledge Deficits in Multi-Modal Language Models"

Official implementation for "Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention" (NeurIPS2024 Spotlight)

[NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

A Comparative Framework for Multimodal Recommender Systems

[TMM'25] Continuously Updated Awesome Multimodal Recommendation Paper List

Short Video Segment-level User Interests Modeling in Personalized Recommendation

Mamba SSM architecture

A unified, comprehensive and efficient recommendation library

[WWW'2023] "MMSSL: Multi-Modal Self-Supervised Learning for Recommendation"

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Github pages backend for https://differentialprivacy.org

[Under Review] Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation

Build resilient language agents as graphs.

🦜🔗 The platform for reliable agents.

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.

A Curated Collection of resources for applied AI engineering (work in progress).

Paper List for Recommend-system PreTrained Models

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

links to conference publications in graph-based deep learning

Benchmark of federated learning. Dedicated to the community. 🤗

This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

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…