THUKEG

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

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

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

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

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

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

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

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

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

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

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

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

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

AgentTuning: Enabling Generalized Agent Abilities for LLMs

Towards Large Multimodal Models as Visual Foundation Agents

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