Skip to content

@JHU-CLSP JHU Center for Language and Speech Processing

Change the repository type filter

All

    Repositories list

    46 repositories

    • al-qasida

      Public
      Python
      •0•1•0•0•Updated Dec 27, 2025Dec 27, 2025

    • science-hierarchography

      Public
      Python
      •3•4•0•0•Updated Dec 15, 2025Dec 15, 2025

    • csci-601-771-self-supervised-models

      Public
      HTML
      •0•0•0•0•Updated Dec 10, 2025Dec 10, 2025

    • MedExpert

      Public
      Code for the "MedExpert: An Expert-Annotated Dataset for Medical Chatbot Evaluation" paper at Machine Learning for Health (ML4H) 2025.
      Python
      •
      MIT License
      •0•6•0•0•Updated Dec 3, 2025Dec 3, 2025

    • RepliCan-C4C

      Public
      Python
      •4•4•0•1•Updated Nov 27, 2025Nov 27, 2025

    • icl-in-genomics-models

      Public
      Essential code for the paper *Genomic Next-Token Predictors are In-Context Learners*.
      Python
      •0•1•0•0•Updated Nov 16, 2025Nov 16, 2025

    • BloomScrub

      Public
      Python
      •0•1•0•0•Updated Nov 5, 2025Nov 5, 2025

    • mmBERT

      Public
      A massively multilingual modern encoder language model
      Python
      •9•117•1•0•Updated Oct 13, 2025Oct 13, 2025

    • Speech_NSF_NextGen

      Public
      NSF CCRI ENS Project: Next Generation Tools for Spoken Language Science & Technology
      1•0•0•0•Updated Oct 1, 2025Oct 1, 2025

    • challenging_the_judge

      Public
      Python
      •0•2•0•0•Updated Sep 23, 2025Sep 23, 2025

    • hell-or-high-water

      Public
      Code and data for the paper: "Hell or High Water: Evaluating Agentic Recovery from External Failures"
      Python
      •
      MIT License
      •0•6•0•0•Updated Aug 14, 2025Aug 14, 2025

    • eval-the-eval-readability

      Public
      Jupyter Notebook
      •0•2•0•0•Updated Aug 11, 2025Aug 11, 2025

    • according-to

      Public
      0•2•0•0•Updated Aug 6, 2025Aug 6, 2025

    • ettin-encoder-vs-decoder

      Public
      State-of-the-art paired encoder and decoder models (17M-1B params)
      Python
      •
      MIT License
      •3•53•0•1•Updated Aug 6, 2025Aug 6, 2025

    • Feedback-Friction

      Public
      Code for paper FEEDBACK FRICTION: LLMs Struggle to Fully Incorporate External Feedback https://arxiv.org/pdf/2506.11930
      Python
      •0•8•0•0•Updated Jun 16, 2025Jun 16, 2025

    • translation-barrier

      Public
      Python
      •1•1•0•0•Updated Jun 12, 2025Jun 12, 2025

    • NeoCoder

      Public
      Official implementation of our paper "Benchmarking Language Model Creativity: A Case Study on Code Generation"
      Python
      •
      Apache License 2.0
      •4•10•0•0•Updated May 16, 2025May 16, 2025

    • ModernBERT

      Public
      Bringing BERT into modernity via both architecture changes and scaling
      Python
      •
      Apache License 2.0
      •136•0•0•0•Updated Apr 22, 2025Apr 22, 2025

    • arXiv2Table

      Public
      Code and dataset for the paper: Can LLMs Generate Tabular Summaries of Science Papers? Rethinking the Evaluation Protocol (https://arxiv.org/pdf/2504.10284)
      Python
      •
      MIT License
      •0•1•2•0•Updated Apr 21, 2025Apr 21, 2025

    • verifiable-by-design

      Public
      Code for paper "Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data"
      Python
      •0•3•0•0•Updated Apr 21, 2025Apr 21, 2025

    • CLAIMCHECK

      Public
      The repo for the paper "CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers? "
      0•0•0•0•Updated Apr 20, 2025Apr 20, 2025

    • web-agent-arena

      Public
      Web Agent Arena
      HTML
      •0•0•0•0•Updated Apr 10, 2025Apr 10, 2025

    • CS-601-471-671-Sp25

      Public
      Python
      •8•6•0•0•Updated Apr 7, 2025Apr 7, 2025

    • icl-ciphers

      Public
      Python
      •1•0•1•0•Updated Feb 15, 2025Feb 15, 2025

    • AnaloBench

      Public
      This project focus on curating a robust analogical reasoning dataset for research and development.
      Python
      •2•5•0•0•Updated Dec 18, 2024Dec 18, 2024

    • turking-bench

      Public
      Web-grounded natural language instructions
      HTML
      •
      Apache License 2.0
      •6•17•3•0•Updated Nov 25, 2024Nov 25, 2024

    • RATIONALYST

      Public
      Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044
      Python
      •5•35•0•0•Updated Oct 3, 2024Oct 3, 2024

    • wikicite

      Public
      Python
      •0•1•0•0•Updated Jul 29, 2024Jul 29, 2024

    • Kreyol-MT

      Public
      Python
      •
      MIT License
      •0•6•0•0•Updated Jun 1, 2024Jun 1, 2024

    • Cost-Effective-Experiment

      Public
      Scripts and docs that help us run cost effective experiment with OpenAI APIs
      Python
      •2•4•0•0•Updated May 28, 2024May 28, 2024