#
Starred repositories
Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"
Balancing Gradient Flow for Universally Better Vision Transformer Attributions
A toolbox to iNNvestigate neural networks' predictions!
Open source interpretability artefacts for R1.
A survey on data-centric foundation models in healthcare.
👋 Xplique is a Neural Networks Explainability Toolbox
👋 Overcomplete is a Vision-based SAE Toolbox
CT-FM: A 3D Image-Based Foundation Model for Computed Tomography
[CVPR 2025] Official Pytorch Code for Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
Training Sparse Autoencoders on Language Models
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
[CVPR 2025 Highlight] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
Layer-Wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]
[ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models
up-to-date curated list of state-of-the-art Large vision language models hallucinations research work, papers & resources
👋 Aligning Human & Machine Vision using explainability
ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
Genome modeling and design across all domains of life
MICV-yonsei / VisAttnSink
Forked from seilk/VisAttnSink[ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models
This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".
Sparsify transformers with SAEs and transcoders