Skip to content

@thu-coai thu-coai

Change the repository type filter

All

    Repositories list

    110 repositories

    • lasa-multilingual-safety

      Public
      【ACL 2026】LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
      0•2•0•0•Updated Apr 23, 2026Apr 23, 2026

    • AISafetyLab

      Public
      AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.
      Python
      •
      MIT License
      •15•241•0•0•Updated Apr 21, 2026Apr 21, 2026

    • EmbodiedAct

      Public
      MATLAB
      •1•0•0•0•Updated Apr 4, 2026Apr 4, 2026

    • CROPI

      Public
      [ACL'26] Official Repository for for paper "Data-Efficient RLVR via Off-Policy Influence Guidance"
      Python
      •0•20•0•0•Updated Mar 29, 2026Mar 29, 2026

    • IF-RewardBench

      Public
      IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation (ACL 2026)
      Python
      •0•4•1•0•Updated Mar 9, 2026Mar 9, 2026

    • Survive-at-All-Costs

      Public
      Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure
      Python
      •
      MIT License
      •1•6•1•0•Updated Mar 6, 2026Mar 6, 2026

    • IF-CRITIC

      Public
      IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation (ACL 2026)
      Shell
      •0•6•2•0•Updated Feb 6, 2026Feb 6, 2026

    • MIR-SafetyBench

      Public
      MIR-SafetyBench: Evaluating Multi-image Reasoning Safety of Multimodal Large Language Models
      Python
      •
      MIT License
      •0•5•0•0•Updated Jan 22, 2026Jan 22, 2026

    • JPS

      Public
      [MM'25] JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
      Python
      •4•20•2•0•Updated Dec 23, 2025Dec 23, 2025

    • Glyph

      Public
      Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
      Python
      •50•587•9•0•Updated Nov 4, 2025Nov 4, 2025

    • SocialEval

      Public
      [ACL'25] SocialEval: Evaluating Social Intelligence of Large Language Models
      Python
      •
      MIT License
      •0•12•0•0•Updated Oct 20, 2025Oct 20, 2025

    • CogFlow

      Public
      Think Socially via Cognitive Reasoning
      Python
      •1•6•0•0•Updated Oct 2, 2025Oct 2, 2025

    • CharacterGLM-6B

      Public
      [EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
      Python
      •
      Apache License 2.0
      •36•501•4•0•Updated Oct 2, 2025Oct 2, 2025

    • Crisp

      Public
      [EMNLP'25] Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues
      Python
      •0•11•1•0•Updated Sep 2, 2025Sep 2, 2025

    • LRM-Safety-Study

      Public
      Python
      •
      MIT License
      •0•6•0•0•Updated Aug 15, 2025Aug 15, 2025

    • Agent-SafetyBench

      Public
      Python
      •
      MIT License
      •9•137•1•0•Updated Aug 11, 2025Aug 11, 2025

    • CharacterBench

      Public
      [AAAI'25] CharacterBench: Benchmarking Character Customization of Large Language Models
      Python
      •1•22•0•0•Updated Aug 1, 2025Aug 1, 2025

    • ShieldVLM

      Public
      Python
      •0•8•0•0•Updated Jul 31, 2025Jul 31, 2025

    • SafetyBench

      Public
      Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]
      Python
      •
      MIT License
      •14•287•0•0•Updated Jul 28, 2025Jul 28, 2025

    • VPO

      Public
      Python
      •
      Apache License 2.0
      •1•25•2•0•Updated Jul 20, 2025Jul 20, 2025

    • LongSafety

      Public
      [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models
      Python
      •
      MIT License
      •0•16•0•0•Updated Jun 18, 2025Jun 18, 2025

    • SPaR

      Public
      Python
      •
      Apache License 2.0
      •3•47•1•0•Updated Jun 11, 2025Jun 11, 2025

    • TransferAttack

      Public
      [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
      Python
      •1•19•0•0•Updated May 23, 2025May 23, 2025

    • HPSS

      Public
      HPSS: Heuristic Prompting Strategy Search for LLM Evaluators (ACL 2025 Findings)
      Python
      •1•3•0•0•Updated May 23, 2025May 23, 2025

    • Backdoor-Data-Extraction

      Public
      Python
      •
      MIT License
      •6•32•1•0•Updated May 22, 2025May 22, 2025

    • BARREL

      Public
      [ICLR 2026] BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
      Python
      •
      MIT License
      •1•18•0•0•Updated May 21, 2025May 21, 2025

    • MAPS

      Public
      Official Implementation of ICLR25 paper "MAPS: Advancing Multi-modal Reasoning in Expert-level Physical Science"
      Python
      •1•10•0•0•Updated Mar 12, 2025Mar 12, 2025

    • ComplexBench

      Public
      Benchmarking Complex Instruction-Following with Multiple Constraints Composition (NeurIPS 2024 Datasets and Benchmarks Track)
      Python
      •
      MIT License
      •12•102•5•0•Updated Feb 20, 2025Feb 20, 2025

    • MiniPLM

      Public
      [ICLR 2025] MiniPLM: Knowledge Distillation for Pre-Training Language Models
      Python
      •
      MIT License
      •9•77•5•0•Updated Nov 23, 2024Nov 23, 2024

    • MoralStory

      Public
      Python
      •1•17•0•0•Updated Nov 7, 2024Nov 7, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.