Stars
TokenSHAP: Explain individual token importance in large language model prompts with SHAP values. Gain insights, debug models, detect biases, and enhance transparency effortlessly
[Pattern Recognition 25] CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks
(TPAMI2022) The ImageNet-S benchmark/method for large-scale unsupervised/semi-supervised semantic segmentation.
Low rank adaptation for Vision Transformer
Modelling human health trajectories using generative transformers
This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaof…
Gemini is a modern LaTex beamerposter theme 🖼
Convert your (Beamer) PDF slides to (Powerpoint) PPTX
ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Learning Convolutional Neural Networks with Interactive Visualization.
A library for mechanistic interpretability of GPT-style language models
This is an official implementation for Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation. [CVPR'25]
A library for feature selection for gradient boosting models using regression on feature Shapley values
Shapley Interactions and Shapley Values for Machine Learning
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
sergregory / HACS-dataset
Forked from hangzhaomit/HACS-datasetHACS: Human Action Clips and Segments Dataset
HACS: Human Action Clips and Segments Dataset
[NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"
A smaller subset of 10 easily classified classes from Imagenet, and a little more French
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Gradient-estimation-based explanation for black-boxes