Skip to content

@thunlp THUNLP

Change the repository type filter

All

    Repositories list

    269 repositories

    • DECO

      Public
      Source code for paper "DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices".
      Python
      •
      Other
      •0•1•0•0•Updated May 12, 2026May 12, 2026

    • OPD

      Public
      Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
      mechanismllmson-policy-distillation
      mechanismllmson-policy-distillation
      Python
      •20•430•2•0•Updated May 12, 2026May 12, 2026

    • ProactiveAgent

      Public
      A LLM-based Agent that predict its tasks proactively.
      Python
      •
      Apache License 2.0
      •58•603•6•0•Updated May 12, 2026May 12, 2026

    • LexRel

      Public
      Python
      •0•1•0•0•Updated May 7, 2026May 7, 2026

    • CPMobius

      Public
      Python
      •
      Apache License 2.0
      •0•1•1•0•Updated Apr 29, 2026Apr 29, 2026

    • JustRL

      Public
      [ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
      Python
      •12•271•0•0•Updated Apr 18, 2026Apr 18, 2026

    • NOSA

      Public
      The official implementation of NOSA
      Python
      •
      MIT License
      •0•17•0•0•Updated Apr 15, 2026Apr 15, 2026

    • hybrid-linear-attention

      Public
      Code and models for the paper: Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
      Python
      •2•36•2•0•Updated Apr 9, 2026Apr 9, 2026

    • APB

      Public
      Official Implementation of APB (ACL 2025 main Oral) and Spava (ACL 2026 main).
      C++
      •5•37•0•0•Updated Apr 6, 2026Apr 6, 2026

    • KARL

      Public
      KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding
      Python
      •
      MIT License
      •1•68•1•0•Updated Apr 5, 2026Apr 5, 2026

    • LexChain

      Public
      Python
      •0•4•1•0•Updated Mar 25, 2026Mar 25, 2026

    • SE-Bench

      Public
      Official repo for "SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization"
      Python
      •
      MIT License
      •4•27•5•0•Updated Mar 24, 2026Mar 24, 2026

    • LLMxMapReduce

      Public
      Python
      •
      Apache License 2.0
      •63•875•0•0•Updated Mar 5, 2026Mar 5, 2026

    • ACDiT

      Public
      ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
      Python
      •
      MIT License
      •1•42•2•0•Updated Jan 29, 2026Jan 29, 2026

    • KG-Infused-RAG

      Public
      Official implementation for the paper "KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs"
      Python
      •1•22•0•0•Updated Jan 18, 2026Jan 18, 2026

    • H-Neurons

      Public
      The official implementation of the paper: H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
      Python
      •
      MIT License
      •11•62•1•0•Updated Jan 14, 2026Jan 14, 2026

    • BlockFFN

      Public
      Source codes for paper "BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity".
      Python
      •5•19•0•0•Updated Jan 10, 2026Jan 10, 2026

    • LLaVA-UHD

      Public
      LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
      Python
      •
      Apache License 2.0
      •21•422•7•0•Updated Dec 20, 2025Dec 20, 2025

    • ChartCoder

      Public
      [ACL'25 Main] ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
      Python
      •5•79•2•0•Updated Dec 8, 2025Dec 8, 2025

    • StateX

      Public
      The official implementation of the paper "StateX: Enhancing RNN Recall via Post-training State Expansion".
      machine-learningmemoryrnn
      machine-learningmemoryrnnrecallssmmambalinear-attentionllmlong-context
      Python
      •0•3•0•0•Updated Oct 24, 2025Oct 24, 2025

    • AgentRM

      Public
      [ACL 2025 main] AgentRM: Enhancing Agent Generalization with Reward Modeling
      Python
      •0•6•1•0•Updated Sep 29, 2025Sep 29, 2025

    • stuffed-mamba

      Public
      The code of the paper Stuffed Mamba: Oversized States Lead to the Inability to Forget
      machine-learningrnnmamba
      machine-learningrnnmambalong-context
      Python
      •0•1•0•0•Updated Sep 28, 2025Sep 28, 2025

    • BurstEngine

      Public
      BurstEngine is an efficient framework designed to train LLMs on long-sequence data.
      Python
      •3•9•0•0•Updated Sep 25, 2025Sep 25, 2025

    • cost-optimal-gqa

      Public
      The code for the paper "Cost-Optimal Grouped-Query Attention for Long-Context Modeling"
      natural-language-processingtransformerattention
      natural-language-processingtransformerattentionlong-contextllms
      Python
      •1•4•1•0•Updated Sep 14, 2025Sep 14, 2025

    • SIR-Bench

      Public
      Python
      •
      Apache License 2.0
      •0•5•1•0•Updated Sep 12, 2025Sep 12, 2025

    • Seq1F1B

      Public
      Sequence-level 1F1B schedule for LLMs.
      Python
      •
      Other
      •4k•37•1•0•Updated Aug 26, 2025Aug 26, 2025

    • FR-Spec

      Public
      [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
      C++
      •3•54•3•0•Updated Jul 15, 2025Jul 15, 2025

    • TritonBench

      Public
      TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
      Python
      •
      Apache License 2.0
      •14•128•4•1•Updated Jun 14, 2025Jun 14, 2025

    • ClueAnchor

      Public
      Python
      •0•10•1•0•Updated Jun 11, 2025Jun 11, 2025

    • TAADpapers

      Public
      Must-read Papers on Textual Adversarial Attack and Defense
      nlpnatural-language-processingadversarial-learning
      nlpnatural-language-processingadversarial-learningadversarial-attackspaper-listadversarial-defense
      Python
      •
      MIT License
      •194•1.6k•3•1•Updated Jun 4, 2025Jun 4, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.