LLaDA2.0-Uni: Understanding and Generation the World.

TIPSv2 (CVPR'26) and TIPS (ICLR'25)

Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database

Official repository for "AM-RADIO: Reduce All Domains Into One"

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

[CVPR 2026] OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks

Learning a dynamic four-chamber shape model of the human heart for 95,695 UK Biobank participants

Official repository for "A Generalizable Deep Learning System for Cardiac MRI"

[CVPR 2026] A mask-guided self-supervised learning method for 3D medical image representation learning

vjepa / vjepa2 / vjepa2.1 PCA visualization utility for dense features and world model inspection.

A clean, single-file PyTorch implementation of Attention Residuals (Kimi Team, MoonshotAI, 2026), integrated with Grouped Query Attention (GQA), SwiGLU feed-forward networks, and Rotary Position Em…

[MIA 2026] MG-3D: Multi-Grained Knowledge-Enhanced Vision-Language Pre-training for 3D Medical Image Analysis

code for "Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging"

Few-Shot Adaptation of Interpretable Deep Multimodal Survival Model Improves Prognostic Prediction in Glioblastoma

U-VLM: Hierarchical Vision Language Modeling for Report Generation

[Nature Machine Intelligence 26] Cardiac Sensing Foundation Model