arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

🎉 TrustJudge is accepted to ICLR 2026!

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

RewardAnything: Generalizable Principle-Following Reward Models

RewardAnything: Generalizable Principle-Following Reward Models

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

RewardBench: the first evaluation tool for reward models.

Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)

A Knowledge-grounded Interactive Evaluation Framework for Large Language Models

[EMNLP'24] FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models (Demo)

[ACL'24] A Knowledge-grounded Interactive Evaluation Framework for Large Language Models

A series of code large language models developed by PKU-KCL

北大选课网补退选阶段自动选课小工具（2023秋-不定长验证码）

Aligning pretrained language models with instruction data generated by themselves.

Robust machine learning for responsible AI

An implementation of the paper "Learning to Reweight Examples for Robust Deep Learning" from ICML 2018 with PyTorch and Higher.

Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction

A PyTorch-based library for semi-supervised learning (NeurIPS'21)

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

Pure python approach of Apache Thrift.

A Multi-modal Model Chinese Spell Checker Released on ACL2021.

LightSeq: A High Performance Library for Sequence Processing and Generation