Skip to content
Change the repository type filter

All

    Repositories list

    • ream

      Public
      REAM: Merging Improves Pruning of Experts in LLMs
      Python
      MIT License
      21300Updated Apr 16, 2026Apr 16, 2026
    • TinyRecursiveModels

      Public archive
      Python
      MIT License
      1k6.5k364Updated Apr 1, 2026Apr 1, 2026
    • 0000Updated Mar 6, 2026Mar 6, 2026
    • nino

      Public
      Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]
      Python
      MIT License
      92800Updated Feb 20, 2026Feb 20, 2026
    • mulo

      Public archive
      μLO: Compute-Efficient Meta-Generalization of Learned Optimizers [to appear at ICLR 2026]
      0000Updated Feb 12, 2026Feb 12, 2026
    • AVR-Eval-Agent

      Public archive
      Python
      MIT License
      21300Updated Aug 18, 2025Aug 18, 2025
    • cont-diffsubmin

      Public archive
      Code for "Discrete and Continuous Difference of Submodular Minimization" [ICML 2025]
      MATLAB
      MIT License
      1000Updated Aug 11, 2025Aug 11, 2025
    • GuidedQuant

      Public archive
      Code for "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" [ICML 2025]
      0000Updated May 20, 2025May 20, 2025
    • ByteCraft

      Public archive
      Python
      MIT License
      64000Updated Apr 9, 2025Apr 9, 2025
    • AnyMolGenCritic

      Public archive
      Python
      MIT License
      62100Updated Apr 3, 2025Apr 3, 2025
    • STGG-AL

      Public archive
      Python
      MIT License
      41300Updated Feb 25, 2025Feb 25, 2025
    • ghn3

      Public archive
      Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]
      Shell
      MIT License
      83800Updated Aug 27, 2024Aug 27, 2024
    • ForestDiffusion

      Public archive
      Generating and Imputing Tabular Data via Diffusion and Flow XGBoost Models
      Python
      1818121Updated Aug 6, 2024Aug 6, 2024
    • LoGAH

      Public archive
      LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters.
      0000Updated May 29, 2024May 29, 2024
    • layer-merge

      Public archive
      Code for "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" [ICML 2024]
      0000Updated May 28, 2024May 28, 2024
    • PAPA

      Public archive
      Repository for the PopulAtion Parameter Averaging (PAPA) paper
      Python
      MIT License
      53000Updated Apr 11, 2024Apr 11, 2024
    • l2o_pytorch

      Public archive
      Simple Learning to Optimize in PyTorch
      Python
      MIT License
      1200Updated Nov 21, 2023Nov 21, 2023
    • Code for "Difference of Submodular Minimization via DC Programming" [ICML 2023]
      MATLAB
      MIT License
      0400Updated May 19, 2023May 19, 2023
    • Code for "Fairness in Streaming Submodular Maximization over a Matroid Constraint" [ICML 2023]
      0000Updated May 5, 2023May 5, 2023
    • subpruning

      Public archive
      Code for "Data-Efficient Structured Pruning via Submodular Optimization" [NeurIPS 2022]
      Jupyter Notebook
      MIT License
      2900Updated May 5, 2023May 5, 2023
    • GGM-metrics

      Public archive
      On Evaluation Metrics for Graph Generative Models [ICLR 2022]
      0100Updated Mar 22, 2023Mar 22, 2023
    • hyper-representation

      Public archive
      Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights [NeurIPS 2022]
      0200Updated Mar 22, 2023Mar 22, 2023
    • multiset-equivariance

      Public archive
      Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation [ICLR 2022]
      0100Updated Mar 13, 2023Mar 13, 2023
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.