Recent studies have observed that intermediate layers of foundation models often yield more discriminative representations than the final layer. While initially attributed to autoregressive pretraining, this phenomenon has also been identified in mod... read more
Finding patient subgroups with similar characteristics is crucial for personalized decision-making in various disciplines such as healthcare and policy evaluation. While most existing approaches rely on unsupervised clustering methods, there is a gro... read more
Nowadays, an increasing number of works fuse LiDAR and RGB data in the bird's-eye view (BEV) space for 3D object detection in autonomous driving systems. However, existing methods suffer from over-reliance on the LiDAR branch, with insufficient explo... read more
Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods accelerate DiT... read more
In clinical prediction settings the importance of a high-dimensional feature like genomics is often assessed by evaluating the change in predictive performance when adding it to a set of traditional clinical variables. This approach is questionable, ... read more
We introduce Dark3R, a framework for structure from motion in the dark that operates directly on raw images with signal-to-noise ratios (SNRs) below $-4$ dB -- a regime where conventional feature- and learning-based methods break down. Our key insigh... read more
Monitoring the health conditions of fish is essential, as it enables the early detection of disease, safeguards animal welfare, and contributes to sustainable aquaculture practices. Physiological and pathological conditions of cultivated fish can be ... read more
The ability to interpret machine learning model decisions is critical in such domains as healthcare, where trust in model predictions is as important as their accuracy. Inspired by the development of prototype parts-based deep neural networks in comp... read more
Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize text-driven amodal 3D generation, where text prompts steer the co... read more
We focus on the task of retrieving nail design images based on dense intent descriptions, which represent multi-layered user intent for nail designs. This is challenging because such descriptions specify unconstrained painted elements and pre-manufac... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.