Stars
WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.
[KDD'26] Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning (LEAP)
A list of recent papers about Link Prediction.
[BIBM 2025] Source code for "CafeMed: Causal Attention Fusion Enhanced Medication Recommendation".
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
This is a repository of open resources for our survey "A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions", TPAMI under review
[NeurIPS 2025] One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
The official implementation of our work SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration in AAAI 2025
EmojiCrypt: Prompt Encryption for Secure Communication with Large Language Models
[EMNLP2025] "RecGPT: A Foundation Model for Sequential Recommendation"
Large Language Model-enhanced Recommender System Papers
Renderer for the harmony response format to be used with gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
KDD 2026 | Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
[ACL 2025] iAgent: LLM Agent as a Shield between User and Recommender Systems
ID-based Graph Recommendation Framework (PyTorch)