Sparse autoencoders for vision
☆55Feb 26, 2026Updated this week
Alternatives and similar repositories for saev
Users that are interested in saev are comparing it to the libraries listed below
Sorting:
- Repository for the BioCLIP 2 model project. [NeurIPS'25 Spotlight] BioCLIP 2 is a biological foundation model trained on TreeOfLife-200M.…☆51Feb 13, 2026Updated 2 weeks ago
- Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.☆18Dec 19, 2024Updated last year
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆18Oct 16, 2024Updated last year
- Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"☆30Oct 31, 2025Updated 4 months ago
- Mujoco sim environment for imitation learning and reinforcement learning with so101 and so100 robots.☆30Jun 30, 2025Updated 8 months ago
- [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"☆95Nov 30, 2025Updated 3 months ago
- ☆25Apr 23, 2024Updated last year
- Official implementation of "PersonaBooth: Personalized Text-to-Motion Generation (CVPR 2025)"☆33Sep 27, 2025Updated 5 months ago
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆29Jun 5, 2025Updated 8 months ago
- [ICML2024] Repo for the paper `Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models'☆22Jan 1, 2025Updated last year
- ☆39Aug 26, 2025Updated 6 months ago
- ☆396Aug 21, 2025Updated 6 months ago
- ☆175Oct 31, 2025Updated 4 months ago
- Code and data for UniEgoMotion (ICCV 2025)☆44Nov 11, 2025Updated 3 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆342Jul 23, 2025Updated 7 months ago
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆63Oct 9, 2025Updated 4 months ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆123Dec 4, 2025Updated 2 months ago
- ☆13Mar 7, 2025Updated 11 months ago
- ☆12May 6, 2022Updated 3 years ago
- Official implementation of "Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation" (NeurIPS 2025)☆18Dec 2, 2025Updated 3 months ago
- MiniGPT-Pancreas: Multimodal Large language Model for Pancreas Cancer Classification and Detection☆11Sep 19, 2025Updated 5 months ago
- [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆64Nov 27, 2025Updated 3 months ago
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆183Sep 26, 2025Updated 5 months ago
- A semi print-in-place hand for human-like manipulation, designed to be built by anyone.☆17Jan 5, 2026Updated last month
- build vgg16 with pytorch 0.4.0 for classification of CIFAR datasets☆10Mar 31, 2019Updated 6 years ago
- ☆31Updated this week
- This repository presents a code to detect the rear of cars using RCNNs. The dataset consists of road images in different conditions like …☆10Apr 15, 2019Updated 6 years ago
- Extract streaming data from text using prefix completion.☆10Oct 6, 2024Updated last year
- Code repository supporting the paper "Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segment…☆11Apr 29, 2024Updated last year
- [ICML 2025] Unlearning in Diffusion Models using Sparse Autoencoders☆52Oct 16, 2025Updated 4 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆60Jul 24, 2025Updated 7 months ago
- [NeurIPS '25 Spotlight] Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"☆172Sep 19, 2025Updated 5 months ago
- [ICLR 2025] Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation☆45Mar 13, 2025Updated 11 months ago
- ☆11Jul 21, 2024Updated last year
- Reconstruction ICA☆10Aug 25, 2017Updated 8 years ago
- USTC-TD☆12Mar 17, 2025Updated 11 months ago
- Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)☆20Jan 17, 2026Updated last month
- Weakly Supervised Object Localization via Class RE-Activation Mapping☆12Sep 19, 2022Updated 3 years ago
- ☆10Oct 17, 2023Updated 2 years ago