maragraziani / concept_discovery_svd
Automatic identification of regions in the latent space of a model that correspond to unique concepts, namely to concepts with a semantically distinct meaning.
☆13Updated last year
Alternatives and similar repositories for concept_discovery_svd:
Users that are interested in concept_discovery_svd are comparing it to the libraries listed below
- Repository for the PopulAtion Parameter Averaging (PAPA) paper☆26Updated last year
- Recycling diverse models☆44Updated 2 years ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆50Updated 11 months ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆62Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆56Updated last year
- Quantification of Uncertainty with Adversarial Models☆28Updated last year
- Official repo of Progressive Data Expansion: data, code and evaluation☆28Updated last year
- Understanding how features learned by neural networks evolve throughout training☆34Updated 6 months ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]☆19Updated last month
- ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"☆68Updated last week
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efficient, non-parametric inf…☆24Updated 6 months ago
- Deep Networks Grok All the Time and Here is Why☆34Updated 11 months ago
- Code for Arxiv Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle☆26Updated last year
- Uncertainty-aware representation learning (URL) benchmark☆103Updated last month
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"☆59Updated 5 months ago
- A reimplementation of 2D Convolutional and Transposed Convolutional Layers in PyTorch, designed for easy modifications and analysis. Incl…☆20Updated last year
- Official code for the paper: "Metadata Archaeology"☆19Updated last year
- ☆15Updated last year
- [ICLR 2024] Easy tools for measuring the label sharpness and intrinsic dimension of datasets and learned representations, which relate to…☆14Updated last month
- Advances in Neural Information Processing Systems (NeurIPS 2021)☆22Updated 2 years ago
- Code for paper: "Privately generating tabular data using language models".☆15Updated last year
- ☆36Updated 2 years ago
- Personal implementation of ASIF by Antonio Norelli☆25Updated 11 months ago
- Library for the Test-based Calibration Error (TCE) metric to quantify the degree to classifier calibration.☆13Updated last year
- ☆26Updated 2 years ago
- A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.☆18Updated 6 months ago
- Sparse and discrete interpretability tool for neural networks☆61Updated last year
- ☆22Updated 4 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- ☆8Updated last year