We present Open-MAGVIT2, a family of auto-regressive image generation models ranging
from 300M to 1.5 B. The Open-MAGVIT2 project produces an open-source replication of …

AI video generation is undergoing a revolution, with quality and realism advancing rapidly.
These advances have led to a passionate scientific debate: Do video models learn``world …

Healthcare systems worldwide face persistent challenges in efficiency, accessibility, and
personalization. Powered by modern AI technologies such as multimodal large language …

Foundation models trained on patient electronic health records (EHRs) require tokenizing
medical data into sequences of discrete vocabulary items. Existing tokenizers treat medical …

This paper aims to improve the performance of video multimodal large language models
(MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of …

Understanding and modeling lighting effects are fundamental tasks in computer vision and
graphics. Classic physically-based rendering (PBR) accurately simulates the light transport …

Latent diffusion models have emerged as the leading approach for generating high-quality
images and videos, utilizing compressed latent representations to reduce the computational …

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation
models leveraging rectified flow Transformers to achieve industry-leading performance. We …

Heterogeneity in sensors and actuators across environments poses a significant challenge
to building large-scale pre-trained world models on top of this low-dimensional sensor …

In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free
paradigm that can make use of adaptive temporal compression in latent space. While …