Zhiwei He

DeepMath. A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

MAPS-mt. [TACL 2024] MAPS enables LLMs🤖 to mimic the human😁 translation process.

X-SIR. [ACL 2024] Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models

SelfTraining4UNMT. [ACL 2022] Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

WMT22-En-Liv. [WMT 2022] Implementation of TAL-SJTU's system for WMT22 English-Livonian

FeedbackMT. Code of "Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model"

LLM-MT-Eval. {DeepL, Google, WMT-Best, davinci-003, turbo, gpt-4} × {En-De, En-Cs, En-Ru, En-Zh, De-Fr, En-Ja, Uk-En, Uk-Cs, En-Hr, En-Ha, En-Is}

RaSA. [ICLR 2025] RaSA: Rank-Sharing Low-Rank Adaptation

corpus-tools. Some useful scripts to process monolingual or parallel texts.

CallOpenAI. Python

verl. veRL: Volcano Engine Reinforcement Learning for LLM

String-Group-By-Parallel-Algorithm. Implementation of string group-by algorithm based on radix sort and parallelized using openmp，MPI and MPI+Openmp.

zwhe99.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

TimedCommitment. The implementation of bitcoin-based timed-commitment scheme from "Secure Multiparty Computations on Bitcoin"

sjtu-ml-proj. Python

zwhe99.