Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching models typica... read more
In-context generation significantly enhances Diffusion Transformers (DiTs) by enabling controllable image-to-image generation through reference examples. However, the resulting input concatenation drastically increases sequence length, creating a sub... read more
Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume model congruity (i.e., the use of fully or partially homogeneous model... read more
While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images. Federated le... read more
Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning required f... read more
While large language models have become the prevailing approach for agentic reasoning and planning, their success in symbolic domains does not readily translate to the physical world. Spatial intelligence, the ability to perceive 3D structure, reason... read more
Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive comparisons. These... read more
We introduce Lunara Aesthetic II, a publicly released, ethically sourced image dataset designed to support controlled evaluation and learning of contextual consistency in modern image generation and editing systems. The dataset comprises 2,854 anchor... read more
We introduce Lunara Aesthetic II, a publicly released, ethically sourced image dataset designed to support controlled evaluation and learning of contextual consistency in modern image generation and editing systems. The dataset comprises 2,854 anchor... read more
We present VRGaussianAvatar, an integrated system that enables real-time full-body 3D Gaussian Splatting (3DGS) avatars in virtual reality using only head-mounted display (HMD) tracking signals. The system adopts a parallel pipeline with a VR Fronten... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.