The official implementation for paper *Causality-Inspired Fair Representation Learning for Multimodal Recommendation*.

The official implementation for paper *Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users*.

(Netflix 2025) Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning

[KDD'2026] "VideoRAG: Chat with Your Videos"

Code for the paper "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"

A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explor…

This repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 25+ specialized domains

Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)

[ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concentrated in low-frequency dimensions across different attentio…

Some GNNs are implemented using PyG for link prediction tasks, including: GCN, GraphSAGE, GAT, Node2Vec、RGCN、HGT and HAN, which will continue to be updated in the future.

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Must-read papers on graph foundation models (GFMs)

Polkadot's ink! to write smart contracts.

[ACL2025] "RecLM: Recommendation Instruction Tuning"

[EMNLP2025] "GraphAgent: Agentic Graph Language Assistant"

OpenAGI: When LLM Meets Domain Experts

[COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?

[WSDM'2024 Oral] "DiffKG: Knowledge Graph Diffusion Model for Recommendation"

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Agent Security Bench (ASB)

AIOS: AI Agent Operating System

[COLM'24] We propose Protein Chain of Thought (ProCoT), which replicates the biological mechanism of signaling pathways as language prompts. It considers a signaling pathway as a protein reasoning …

Source Code for ECE445/ME470 Senior Design Project, Running on Rasperry Pi 5B

The official Meta Llama 3 GitHub site

[Preprint] Large Language Model-based Stock Trading in Simulated Real-world Environments

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"