Lists (6)
🦌Data-Centric AI
🐍LLM Alignment
🦕Multi-modal KG
Repos of multi-modal knowledge graphs.🐎Multi-modal LLMs
🐓Open-Source LLMs
🐂Recommendation
Repos of recommendation systems (both traditional methods and LLM-based methods).Stars
CMMLU: Measuring massive multitask language understanding in Chinese
[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"
Repo for adapting Meta LlaMA2 in Chinese! META最新发布的LlaMA2的汉化版！ （完全开源可商用）
Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
PyTorch reimplementation of Diffusion Models
[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models
[WSDM'2024 Oral] "SSLRec: A Self-Supervised Learning Framework for Recommendation"
An open collection of implementation tips, tricks and resources for training large language models
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"
MLNLP社区用来帮助缩短参考文献的工具。A tool for simplifying bibtex with official info
LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
Several data modalities for KBs (visual, numerical, temporal, etc.)
[Tool] For Knowledge Graph Representation Learning
MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKU
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
Unbiased Learning To Rank Algorithms (ULTRA)
[Paper][AAAI 2025] (MyGO)Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation
The official implementation of 1. Achieving Cross Modal Generalization with Multimodal Unified Representation (NeurIPS '23) 2. Open-set Cross Modal Generalization via Multimodal Unified Representat…
spaCy module for linking text to Wikidata items
Code for "KBGAN: Adversarial Learning for Knowledge Graph Embeddings" https://arxiv.org/abs/1711.04071
[Paper][ACM MM 2024] Making Large Language Models Perform Better in Knowledge Graph Completion
[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct
[ICCV 2025 Highlight] The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"