Repository of AAAI26 paper 'Flexible Concept Bottleneck Model'.

This repo contains documentation and code needed to use PACO dataset: data loaders and training and evaluation scripts for objects, parts, and attributes prediction models, query evaluation scripts…

Official implementation of MAIA, A Multimodal Automated Interpretability Agent

Mechanistic understanding and validation of large AI models with SemanticLens

LongLive: Real-time Interactive Long Video Generation

Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]

Probabilistic cell segmentation for in situ spatial transcriptomics

[NeurIPS'25 Spotlight] (DANCE) Disentangled Concepts Speak Louder Than Words:Explainable Video Action Recognition official code repository

Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch

Official implementation of paper: Characterizing Dataset Bias via Disentangled Visual Concepts

A tool for matching points annotation

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[CVPR 2025] Official implementation of the paper "Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models" (by Benou and Riklin-Raviv): https://arxiv.org/…

✨✨[NeurIPS 2025] This is the official implementation of our paper "Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension"

Official repo for paper: "GRACE: Generative Representation Learning via Contrastive Policy Optimization"

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

LaTeX template for dissertations in Peking University

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Training Sparse Autoencoders on Language Models

Universal Image Restoration Pre-training via Masked Degradation Classification

Merlin is a 3D VLM for computed tomography that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining.

A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

[Nature Machine Intelligence 2024] Code and evaluation repository for the paper

Documentation for iNaturalist Open Data