We propose a novel method for establishing correspondence between two sequences of 2D images. One particular application of this technique is slice-level content navigation, where the goal is to localize specific 2D slices within a 3D volume or deter... read more
Negation is a fundamental linguistic operation in clinical reporting, yet vision-language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce a radiolo... read more
Robots operating in the real world must plan through environments that deform, yield, and reconfigure under contact, requiring interaction-aware 3D representations that extend beyond static geometric occupancy. To address this, we introduce neural ta... read more
Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of vectors, making indexing and search increasingly expensive. We present Visual RAG Toolkit, a ... read more
Significant differences in optical images and Synthetic Aperture Radar (SAR) images are caused by fundamental differences in the physical principles underlying their acquisition by Earth remote sensing platforms. These differences make precise image ... read more
As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems. Nevertheless, pre-tra... read more
Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We introduce F... read more
Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under different data distributions. While domain adaptation (DA) methods can mitigate such shifts, its "black-box... read more
Event-based vision encodes dynamic scenes as asynchronous spatio-temporal spikes called events. To leverage conventional image processing pipelines, events are typically binned into frames. However, binning functions are discontinuous, which truncate... read more
Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger models and rela... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.