maragraziani / concept_discovery_svdLinks
Automatic identification of regions in the latent space of a model that correspond to unique concepts, namely to concepts with a semantically distinct meaning.
β14Updated 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
Sorting:
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β66Updated 2 years ago
- Recycling diverse modelsβ45Updated 2 years ago
- Uncertainty-aware representation learning (URL) benchmarkβ105Updated 5 months ago
- Understanding how features learned by neural networks evolve throughout trainingβ36Updated 9 months ago
- β31Updated last year
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"β53Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithmsβ59Updated last year
- Deep Networks Grok All the Time and Here is Whyβ37Updated last year
- Repository for the PopulAtion Parameter Averaging (PAPA) paperβ26Updated last year
- A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.β18Updated 9 months ago
- ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"β109Updated last month
- π Overcomplete is a Vision-based SAE Toolboxβ71Updated last week
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmindβ66Updated 10 months ago
- Code for paper: "Privately generating tabular data using language models".β15Updated 2 years ago
- Personal implementation of ASIF by Antonio Norelliβ25Updated last year
- β69Updated 11 months ago
- Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurIβ¦β90Updated last year
- Making Heads or Tails Towards Semantically Consistent Visual Counterfactualsβ30Updated 2 years ago
- Sparse and discrete interpretability tool for neural networksβ63Updated last year
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efο¬cient, non-parametric infβ¦β24Updated 9 months ago
- Advances in Neural Information Processing Systems (NeurIPS 2021)β22Updated 2 years ago
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.β20Updated last year
- [CVPR'23 Highlight] Heterogeneous Continual Learning.β16Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabsβ36Updated 2 years ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]β19Updated 2 months ago
- Conformal prediction for controlling monotonic risk functions. Simple accompanying PyTorch code for conformal risk control in computer viβ¦β67Updated 2 years ago
- Quantification of Uncertainty with Adversarial Modelsβ30Updated 2 years ago
- Collection of tests performed during the study of the new Kolmogorov-Arnold Neural Networks (KAN)β39Updated 5 months ago
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"β60Updated 8 months ago
- Meta-Album meta-dataset for few-shot image classificationβ24Updated 2 years ago