dynamical-inference / patchsaeLinks
Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
☆15Updated last month
Alternatives and similar repositories for patchsae
Users that are interested in patchsae are comparing it to the libraries listed below
Sorting:
- What do we learn from inverting CLIP models?☆55Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆102Updated 2 years ago
- Sparse autoencoders for vision☆36Updated this week
- Code for Debiasing Vision-Language Models via Biased Prompts☆56Updated 2 years ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆39Updated 7 months ago
- ☆22Updated last year
- Code for the paper - ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning☆19Updated 10 months ago
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆31Updated last year
- Erasing conceptual knowledge from language models through low-rank fine-tuning☆18Updated 2 months ago
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆75Updated 3 weeks ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆29Updated 7 months ago
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆27Updated last year
- ☆57Updated 7 months ago
- Model Merging with SVD to Tie the KnOTS [ICLR 2025]☆57Updated 2 months ago
- Official codebase for the NeurIPS 2023 paper: Towards Last-layer Retraining for Group Robustness with Fewer Annotations. https://arxiv.or…☆11Updated last year
- ☆42Updated 9 months ago
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).☆25Updated 5 months ago
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆19Updated 2 months ago
- Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)☆10Updated 10 months ago
- Official Code Release for "Diagnosing and Rectifying Vision Models using Language" (ICLR 2023)☆34Updated 2 years ago
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆57Updated last year
- [CVPR 2024 Highlight] OpenBias: Open-set Bias Detection in Text-to-Image Generative Models☆24Updated 4 months ago
- ☆24Updated 3 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆37Updated 7 months ago
- Official repo for Detecting, Explaining, and Mitigating Memorization in Diffusion Models (ICLR 2024)☆75Updated last year
- ☆107Updated last year
- 🔥 [ICLR 2025] Official PyTorch Model "Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark"☆15Updated 4 months ago
- Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Expl…☆12Updated 2 months ago
- ☆37Updated 11 months ago
- ☆30Updated 11 months ago