[COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Code for the experiments and websites of the paper "Same Task, Different Circuits"

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

XL-VLMs: General Repository for eXplainable Large Vision Language Models

Generic template to bootstrap your Python project.

Code for "ResiDual Transformer Alignment with Spectral Decomposition", TMLR 2025

Fast, differentiable sorting and ranking in PyTorch

Code and data for the paper "Emergent Visual-Semantic Hierarchies in Image-Text Representations" (ECCV 2024)

This is the official GitHub for paper: On the Versatile Uses of Partial Distance Correlation in Deep Learning, in ECCV 2022

official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models (ICCV 2023)

A Python package for analyzing and transforming neural latent spaces.

[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Implementation of the Tolman Eichenbaum Machine in pytorch

Escaping the Big Data Paradigm with Compact Transformers, 2021 (Train your Vision Transformers in 30 mins on CIFAR-10 with a single GPU!)

Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.

Code for "Unifying Grokking and Double Descent" from the NeurIPS 2022 ML Safety Workshop.

Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation

Official code repository for Prompt-DT.

find clusters of different intrinsic dimension

Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for mujoco control tasks in OpenAI gym

An unofficial implementation for online decision transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

A Python library for Secure and Explainable Machine Learning