Skip to content

@hkust-nlp NLP Group @ HKUST

Change the repository type filter

All

    Repositories list

    31 repositories

    • entropy-centroid

      Public
      Python
      •0•1•0•0•Updated Apr 24, 2026Apr 24, 2026

    • Toolathlon

      Public
      [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
      Python
      •33•336•7•1•Updated Apr 23, 2026Apr 23, 2026

    • comp5212_2026spring_pj

      Public
      Python
      •7•8•0•0•Updated Apr 2, 2026Apr 2, 2026

    • LOCA-bench

      Public
      Benchmarking Language Agents Under Controllable and Extreme Context Growth
      Python
      •
      MIT License
      •5•37•1•0•Updated Mar 30, 2026Mar 30, 2026

    • KernelGYM

      Public
      [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations
      Python
      •18•160•3•1•Updated Mar 29, 2026Mar 29, 2026

    • AgentVista

      Public
      Benchmarking multimodal agents on realistic, ultra-challenging visual scenarios requiring long-horizon hybrid tool use.
      Python
      •5•51•0•0•Updated Mar 10, 2026Mar 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".
      Python
      •
      MIT License
      •0•17•0•0•Updated Feb 9, 2026Feb 9, 2026

    • simpleRL-reason

      Public
      Simple RL training for reasoning
      Python
      •
      MIT License
      •289•3.8k•33•1•Updated Dec 23, 2025Dec 23, 2025

    • COMP4901B-LLMs

      Public
      "Large Language Models" Course (COMP4901B) offered in HKUST
      Python
      •12•10•0•1•Updated Nov 23, 2025Nov 23, 2025

    • deepsearch-tts

      Public
      Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
      Python
      •1•22•1•0•Updated Oct 8, 2025Oct 8, 2025

    • RL-Verifier-Robustness

      Public
      From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.
      Python
      •
      MIT License
      •1•25•0•0•Updated Oct 7, 2025Oct 7, 2025

    • WebExplorer

      Public
      The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"
      Python
      •3•115•1•0•Updated Sep 29, 2025Sep 29, 2025

    • ceval

      Public
      Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]
      Python
      •
      MIT License
      •83•1.8k•6•0•Updated Jul 27, 2025Jul 27, 2025

    • mstar

      Public
      [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning
      MIT License
      •3•73•2•0•Updated Jul 13, 2025Jul 13, 2025

    • Laser

      Public
      [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
      Python
      •3•64•4•0•Updated May 22, 2025May 22, 2025

    • B-STaR

      Public
      B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
      Python
      •11•86•0•0•Updated May 21, 2025May 21, 2025

    • CodeIO

      Public
      [ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
      Python
      •34•568•0•1•Updated May 6, 2025May 6, 2025

    • GUIMid

      Public
      0•22•1•0•Updated May 3, 2025May 3, 2025

    • Vision4Chart

      Public
      The official repo of "On the Perception Bottleneck of VLMs for Chart Understanding"
      Jupyter Notebook
      •0•9•0•0•Updated Apr 12, 2025Apr 12, 2025

    • PreSelect

      Public
      [ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches
      Python
      •9•64•0•0•Updated Mar 4, 2025Mar 4, 2025

    • dart-math

      Public
      [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
      nlpdeep-learningmathematics
      nlpdeep-learningmathematicsllmllm-trainingllm-inferencellm-evaluation
      Jupyter Notebook
      •
      MIT License
      •7•121•5•0•Updated Dec 10, 2024Dec 10, 2024

    • deita

      Public
      Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
      alignmentdata-centriclarge-language-models
      alignmentdata-centriclarge-language-modelsinstruction-tuning
      Python
      •
      Apache License 2.0
      •35•594•9•0•Updated Dec 9, 2024Dec 9, 2024

    • Universal_Truthfulness_Hyperplane

      Public
      On the Universal Truthfulness Hyperplane Inside LLMs (EMNLP 2024)
      Python
      •2•6•0•0•Updated Oct 3, 2024Oct 3, 2024

    • llm-compression-intelligence

      Public
      Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]
      Python
      •
      MIT License
      •7•147•0•0•Updated Sep 20, 2024Sep 20, 2024

    • AgentBoard

      Public
      An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]
      SAS
      •41•409•12•5•Updated May 20, 2024May 20, 2024

    • Activation_Decoding

      Public
      In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)
      Python
      •9•62•3•1•Updated Mar 30, 2024Mar 30, 2024

    • hkust-nlp.github.io

      Public
      JavaScript
      •1•0•0•0•Updated Jan 25, 2024Jan 25, 2024

    • felm

      Public
      Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)
      Python
      •1•64•3•0•Updated Dec 25, 2023Dec 25, 2023

    • PEM_composition

      Public
      [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"
      Python
      •
      Apache License 2.0
      •9•61•4•1•Updated Nov 26, 2023Nov 26, 2023

    • llmeval_sum_factual

      Public
      Python
      •1•7•0•0•Updated Oct 3, 2023Oct 3, 2023
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.