Skip to content
Change the repository type filter

All

    Repositories list

    • Rethinking the Role of Efficient Attention in Hybrid Architectures
      Python
      MIT License
      0100Updated Jun 17, 2026Jun 17, 2026
    • NOSA

      Public
      The official implementation of NOSA
      Python
      MIT License
      01700Updated Jun 11, 2026Jun 11, 2026
    • OPD

      Public
      Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
      Python
      4368720Updated May 30, 2026May 30, 2026
    • DECO

      Public
      Source code for paper "DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices".
      Python
      Other
      0200Updated May 12, 2026May 12, 2026
    • A LLM-based Agent that predict its tasks proactively.
      Python
      Apache License 2.0
      6261260Updated May 12, 2026May 12, 2026
    • LexRel

      Public
      Python
      0100Updated May 7, 2026May 7, 2026
    • CPMobius

      Public
      Python
      Apache License 2.0
      0110Updated Apr 29, 2026Apr 29, 2026
    • JustRL

      Public
      [ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
      Python
      1327910Updated Apr 18, 2026Apr 18, 2026
    • Code and models for the paper: Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
      Python
      23610Updated Apr 9, 2026Apr 9, 2026
    • APB

      Public
      Official Implementation of APB (ACL 2025 main Oral) and Spava (ACL 2026 main).
      C++
      53700Updated Apr 6, 2026Apr 6, 2026
    • KARL

      Public
      KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding
      Python
      MIT License
      16810Updated Apr 5, 2026Apr 5, 2026
    • LexChain

      Public
      Python
      0410Updated Mar 25, 2026Mar 25, 2026
    • SE-Bench

      Public
      Official repo for "SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization"
      Python
      MIT License
      42850Updated Mar 24, 2026Mar 24, 2026
    • Python
      Apache License 2.0
      6287400Updated Mar 5, 2026Mar 5, 2026
    • ACDiT

      Public
      ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
      Python
      MIT License
      14220Updated Jan 29, 2026Jan 29, 2026
    • Official implementation for the paper "KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs"
      Python
      12300Updated 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
      136610Updated 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
      51900Updated 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
      2042470Updated Dec 20, 2025Dec 20, 2025
    • [ACL'25 Main] ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
      Python
      57930Updated Dec 8, 2025Dec 8, 2025
    • StateX

      Public
      The official implementation of the paper "StateX: Enhancing RNN Recall via Post-training State Expansion".
      Python
      0300Updated Oct 24, 2025Oct 24, 2025
    • AgentRM

      Public
      [ACL 2025 main] AgentRM: Enhancing Agent Generalization with Reward Modeling
      Python
      0610Updated Sep 29, 2025Sep 29, 2025
    • The code of the paper Stuffed Mamba: Oversized States Lead to the Inability to Forget
      Python
      0100Updated Sep 28, 2025Sep 28, 2025
    • BurstEngine is an efficient framework designed to train LLMs on long-sequence data.
      Python
      3900Updated Sep 25, 2025Sep 25, 2025
    • The code for the paper "Cost-Optimal Grouped-Query Attention for Long-Context Modeling"
      Python
      1410Updated Sep 14, 2025Sep 14, 2025
    • SIR-Bench

      Public
      Python
      Apache License 2.0
      0510Updated Sep 12, 2025Sep 12, 2025
    • Seq1F1B

      Public
      Sequence-level 1F1B schedule for LLMs.
      Python
      Other
      4.1k3710Updated Aug 26, 2025Aug 26, 2025
    • FR-Spec

      Public
      [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
      C++
      35530Updated Jul 15, 2025Jul 15, 2025
    • TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
      Python
      Apache License 2.0
      1413441Updated Jun 14, 2025Jun 14, 2025
    • [EMNLP 2025 Findings] ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
      Python
      01210Updated Jun 11, 2025Jun 11, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.