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 2 years ago
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:
- Uncertainty-aware representation learning (URL) benchmarkβ105Updated 9 months ago
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β71Updated 2 years ago
- β33Updated last year
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efο¬cient, non-parametric infβ¦β25Updated last year
- Recycling diverse modelsβ46Updated 2 years ago
- Understanding how features learned by neural networks evolve throughout trainingβ40Updated last year
- Deep Networks Grok All the Time and Here is Whyβ38Updated last year
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"β55Updated last year
- Personal implementation of ASIF by Antonio Norelliβ26Updated last year
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmindβ72Updated last year
- Repository for the PopulAtion Parameter Averaging (PAPA) paperβ28Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithmsβ58Updated 2 years ago
- ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"β117Updated 5 months ago
- Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurIβ¦β93Updated last year
- Conformal prediction for controlling monotonic risk functions. Simple accompanying PyTorch code for conformal risk control in computer viβ¦β72Updated 2 years ago
- π Overcomplete is a Vision-based SAE Toolboxβ106Updated last week
- Official Implementation of the paper: "A Rate-Distorion View of Uncertainty Quantification", ICML 2024β28Updated last year
- Exact method for visualizing partitions of a Deep Neural Network, CVPR 2023 Highlightβ110Updated 10 months ago
- β69Updated last year
- Conference schedule, top papers, and analysis of the data for NeurIPS 2023!β121Updated last year
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]β90Updated 2 years ago
- [CVPR'23 Highlight] Heterogeneous Continual Learning.β15Updated 2 years ago
- Official repo of Progressive Data Expansion: data, code and evaluationβ29Updated 2 years ago
- Extending Conformal Prediction to LLMsβ68Updated last year
- β15Updated 9 months ago
- Quantification of Uncertainty with Adversarial Modelsβ29Updated 2 years ago
- A repository to house some personal attempts to beat some state-of-the-art for medical datasetsβ100Updated 2 years ago
- [ICCV25] Official Implementation of LeGradβ83Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabsβ36Updated 3 years ago
- Sparse and discrete interpretability tool for neural networksβ64Updated last year