Medical image segmentation has been significantly advanced with the rapid development of deep learning (DL) techniques. Existing DL-based segmentation models are typically discriminative; i.e., they aim to learn a mapping from the input image to segm...
Human organs constantly undergo anatomical changes due to a complex mix of short-term (e.g., heartbeat) and long-term (e.g., aging) factors. Evidently, prior knowledge of these factors will be beneficial when modeling their future state, i.e., via im...
We construct a sequence of functions that uniformly converge (on compact sets) to the price of Asian option, which is written on a stock whose dynamics follows a jump diffusion, exponentially fast. Each of the element in this sequence solves a para...
We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which animates a reference portrait with target landmark sequences. The main challenge of portrait animation is to preserve the identity of the reference portrait and t...
Remote sensing image object detection (RSIOD) aims to identify and locate specific objects within satellite or aerial imagery. However, there is a scarcity of labeled data in current RSIOD datasets, which significantly limits the performance of curre...
A large scale agent-based model of common Facebook users was designed to develop an understanding of the underlying mechanism of information diffusion within online social networks at a micro-level analysis. The agent-based model network structure is...
During embryo development, patterns of protein concentration appear in response to morphogen gradients. These patterns provide spatial and chemical information that directs the fate of the underlying cells. Here, we emulate this process within non-li...
We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER). GEOMANCER provides a partial answer to the question posed by Higgins et al. (2018): is it possible...
Recent diffusion models achieve personalization by learning specific subjects, allowing learned attributes to be integrated into generated images. However, personalized human image generation remains challenging due to the need for precise and consis...
Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited to object-level generation. W...
We've joined forces with @johnowhitaker to launch a new course on Diffusion Models ?! Come learn the nuts and bolts of generative ML and how to train models that ...
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance Dongmin Park · Sebin Kim · Taehong Moon · Minkyu Kim · Kangwook Lee · Jaewoong Cho 2025 Poster [ Slides] [ OpenReview]
A celebration for Stability AI, the start-up behind the controversial Stable Diffusion image generator, represents the arrival of a new A.I. boom.
Google is launching Jetstream, a new engine to run generative AI models, and MaxDiffusion, a collection of reference implementations of various diffusion models.
A celebration for Stability AI, the start-up behind the controversial Stable Diffusion image generator, represents the arrival of a new A.I. boom.