THUKEG ORG

GLM (General Language Model)

slime is an LLM post-training framework for RL Scaling.

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

RL Scaling and Test-Time Scaling (ICML'25)

Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

AgentTuning: Enabling Generalized Agent Abilities for LLMs

LongBench v2 and LongBench (ACL 25'&24')

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

An LLM-based Web Navigating Agent (KDD'24)

GraphMAE: Self-Supervised Masked Graph Autoencoders in KDD'22

INFTY Engine: An Optimization Toolkit to Support Continual AI

Source code and dataset for KDD 2019 paper "Representation Learning for Attributed Multiplex Heterogeneous Network"

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Source code and dataset for ACL 2019 paper "Cognitive Graph for Multi-Hop Reading Comprehension at Scale"

大模型多维度中文对齐评测基准 (ACL 2024)

Revisiting, benchmarking, and refining Heterogeneous Graph Neural Networks.

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training @ KDD 2020

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Official Pytorch Implementation for MathGLM

No description.

Source code and dataset for KDD 2020 paper "Controllable Multi-Interest Framework for Recommendation"

Towards Large Multimodal Models as Visual Foundation Agents

[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs

Towards Knowledge-Based Personalized Product Description Generation in E-commerce @ KDD 2019

Source code and dataset for IJCAI 2019 paper "ProNE: Fast and Scalable Network Representation Learning"

Paper list of NLP for recommender systems

No description.

Source code and dataset of the NeurIPS 2020 paper "Graph Random Neural Network for Semi-Supervised Learning on Graphs"

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner in WWW'23

A unified tokenization tool for Images, Chinese and English.

Towards Knowledge-Based Recommender Dialog System @ EMNLP 2019

Finetuning and inference tools for the CogView4 and CogVideoX model series.

Protein Language Model

Code, Data and Demo for Paper: Controllable Generation from Pre-trained Language Models via Inverse Prompting

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Source code and dataset for KDD 2020 paper "Understanding Negative Sampling in Graph Representation Learning"

Parameter-Efficient Fine-Tuning for Foundation Models

Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.

TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25

No description.

SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning (NeurIPS D&B Track 2024)

kgTransformer: pre-training for reasoning over complex KG queries (KDD 22)

Implementation of "GraphSGAN", a GAN-based semi-supervised learning algorithm for graph data.

No description.

No description.

A heterogeneous entity-augmented academic language model based on Open Academic Graph (OAG)

Source code and dataset for KDD 2019 paper "Sequential Scenario-Specific Meta Learner for Online Recommendation"

Codes for WWW2022 accepted paper: SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs

This repository contains the code and data for the paper "Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards".

Source code and dataset for paper "Cognitive Knowledge Graph Reasoning for One-shot Relational Learning"

NaturalCodeBench (Findings of ACL 2024)

No description.

The multilingual variant of GLM, a general language model trained with autoregressive blank infilling objective

DataSciBench: An LLM Agent Benchmark for Data Science (Findings of ACL 2026)

No description.

[ACL25' Findings] SWE-Dev is an SWE agent with a scalable test case construction pipeline.

Source code and dataset for KDD 2019 paper "OAG: Toward Linking Large-scale Heterogeneous Entity Graphs"

No description.

KDD'23 Web-Scale Academic Name Disambiguation: the WhoIsWho Benchmark, Leaderboard, and Toolkit

Daily reading group on graphs at KEG

No description.

Source code of paper: A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models. (ICML 2025)

MSAGPT

Transformer related optimization, including BERT, GPT

[ACL 2025 Main] SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

SCR: Training Graph Neural Networks with Consistency Regularization

Code and dataset for paper "GRAND+: Scalable Graph Random Neural Networks"

Inference speed-up for stable-diffusion (ldm) with TensorRT.

TKDE'22-GraphCAD: https://arxiv.org/pdf/2108.07516.pdf

RecDCL: Dual Contrastive Learning for Recommendation (WWW'24, Oral)

Course Materials for ML Course at Tsinghua

A convenient framework for developing LLM- and LMM-based web agents. (ACL'24 Demo)

ApeGNN: Node-Wise Adaptive Aggregation in GNNs for Recommendation (WWW'23)

A list of recent industrial papers in KDD'16–'18

code for paper TDGIA:Effective Injection Attacks on Graph Neural Networks (KDD 2021, research track)

A task relevant entity linking toolkit

Graph Injection Adversarial Attack & Defense Dataset , extracted from KDD CUP 2020 ML2 Track

No description.

Extensive Self-Contrast Enables Feedback-Free Language Model Alignment

Apply Iprompt on GLM with innovative new methods. Currently support Chinese QA, English QA and Chinese poem generation.

No description.

No description.

The source code for BatchSampler that accepted in KDD'23

Reinforcing LLM Reasoning through Self-Training and Value-Guided Decoding

GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment

MRT: Tracing the Evolution of Scientific Publications (TKDE 2021)

Source code and dataset for TKDE 2019 paper “Trust Relationship Prediction in Alibaba E-Commerce Platform”

No description.

Source code for EMNLP2022 long paper: Parameter-Efficient Tuning Makes a Good Classification Head

APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding

No description.

No description.

Source code and dataset for IJCAI 2022 paper "Rethinking the Setting of Semi-supervised Learning on Graphs"

No description.

No description.

No description.

No description.

Typescript SDK for Z.ai - Not yet released.

No description.

pix2struct version of open_clip

MCAP: Low-Pass GNNs with Matrix Completion for Academic Recommendations (TOIS'24)

No description.

code, data and model for Paper: AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models (ACL'25 main)

code and data for Paper: BIPro: Zero-shot Chinese Poem Generation via Block Inverse Prompting Constrained Generation Framework(ACL 2025 main)

No description.

No description.

No description.

No description.

Official Pytorch Implementation for MathGLM-Vision

DropConn: Dropout Connection Based Random GNNs for Molecular Property Prediction (TKDE'24)

No description.

Source code and dataset for WWW'22 paper "STAM: A Spatiotemporal Aggregation Method for Graph Neural Network-based Recommendation"

Source code and dataset for TKDE'22 paper "Region or Global? A Principle for Negative Sampling in Graph-based Recommendation"

No description.

No description.

No description.

Ongoing research training transformer models at scale

CodeRM-NT: Reward Model for Code RL without Unit Tests (Findings of ACL 2026)

No description.

Official Pytorch Implementation for VisScience

A Pre-training Framework for Adaptive Learning in MOOCs