Trustworthy-ML-Lab / Linear-ExplanationsLinks
[ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks
☆13Updated 3 months ago
Alternatives and similar repositories for Linear-Explanations
Users that are interested in Linear-Explanations are comparing it to the libraries listed below
Sorting:
- [TMLR 25] An automated method for explaining complex neuron behaviors in deep vision models using large language models☆10Updated 5 months ago
- Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.☆16Updated last year
- What do we learn from inverting CLIP models?☆55Updated last year
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆31Updated last year
- Official codebase for the NeurIPS 2023 paper: Towards Last-layer Retraining for Group Robustness with Fewer Annotations. https://arxiv.or…☆11Updated last year
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated 2 years ago
- AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies☆23Updated 11 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 9 months ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆39Updated 8 months ago
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆24Updated 3 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Updated last year
- ☆22Updated 2 months ago
- Bias-to-Text: Debiasing Unknown Visual Biases through Language Interpretation☆31Updated 2 years ago
- LCA-on-the-line (ICML 2024 Oral)☆12Updated 5 months ago
- If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions☆17Updated last year
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆56Updated 2 years ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆103Updated 2 years ago
- [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang☆16Updated 2 years ago
- ☆15Updated 11 months ago
- ☆34Updated last year
- ☆17Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆49Updated last year
- Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning (ICML 2023)☆18Updated last year
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Updated 2 years ago
- ☆25Updated 2 years ago
- Code for T-MARS data filtering☆35Updated last year
- (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation☆41Updated last year
- ☆14Updated 6 months ago
- [NeurIPS2023] "Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning" by Yihua Zhang*, Yimeng Zhang*,…☆13Updated last year
- Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Expl…☆12Updated 4 months ago