Skip to content
@hkust-nlp

NLP Group @ HKUST

We are a group of NLP researchers in the Hong Kong University of Science and Technology

Pinned Loading

  1. simpleRL-reason simpleRL-reason Public

    Simple RL training for reasoning

    Python 3.8k 289

  2. CodeIO CodeIO Public

    [ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

    Python 568 33

  3. deita deita Public

    Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

    Python 593 35

  4. ceval ceval Public

    Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

    Python 1.8k 82

  5. Toolathlon Toolathlon Public

    [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

    Python 315 32

  6. KernelGYM KernelGYM Public

    [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations

    Python 156 17

Repositories

Showing 10 of 30 repositories
  • hkust-nlp/comp5212_2026spring_pj’s past year of commit activity
    Python 8 7 0 0 Updated Apr 2, 2026
  • Toolathlon Public

    [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

    hkust-nlp/Toolathlon’s past year of commit activity
    Python 315 32 6 0 Updated Mar 31, 2026
  • LOCA-bench Public

    Benchmarking Language Agents Under Controllable and Extreme Context Growth

    hkust-nlp/LOCA-bench’s past year of commit activity
    Python 35 MIT 3 1 0 Updated Mar 30, 2026
  • KernelGYM Public

    [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations

    hkust-nlp/KernelGYM’s past year of commit activity
    Python 156 17 3 1 Updated Mar 29, 2026
  • AgentVista Public

    Benchmarking multimodal agents on realistic, ultra-challenging visual scenarios requiring long-horizon hybrid tool use.

    hkust-nlp/AgentVista’s past year of commit activity
    Python 50 5 0 0 Updated Mar 10, 2026
  • model-task-align-rl Public

    [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".

    hkust-nlp/model-task-align-rl’s past year of commit activity
    Python 17 MIT 0 0 0 Updated Feb 9, 2026
  • simpleRL-reason Public

    Simple RL training for reasoning

    hkust-nlp/simpleRL-reason’s past year of commit activity
    Python 3,846 MIT 289 33 1 Updated Dec 23, 2025
  • COMP4901B-LLMs Public

    "Large Language Models" Course (COMP4901B) offered in HKUST

    hkust-nlp/COMP4901B-LLMs’s past year of commit activity
    Python 10 12 0 1 Updated Nov 23, 2025
  • deepsearch-tts Public

    Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification

    hkust-nlp/deepsearch-tts’s past year of commit activity
    Python 22 1 1 0 Updated Oct 8, 2025
  • RL-Verifier-Robustness Public

    From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.

    hkust-nlp/RL-Verifier-Robustness’s past year of commit activity
    Python 25 MIT 1 0 0 Updated Oct 7, 2025

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…