Whole-slide image (WSI) multiple instance learning (MIL) classifiers can achieve strong slide-level AUC while leaving the full-bag prediction opaque. Attention scores are widely reused as post-hoc explanations, but high attention can reflect aggregat... read more
Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permits a closed-form solution for the output layer. However, conventional random initialization is bli... read more
Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives with correct object counts, classes, and approximate positions, yet the same models fail at simpler spa... read more
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from strong motion... read more
Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains a significant bottleneck. In this paper, we propose Clear2Fog (C2F), an end-to-end, physics-based ... read more
The perceptual representations supporting our ability to recognize faces remain a computational mystery. Deep neural networks offer mechanistic hypotheses for human face perception, but theoretically distinct models often make indistinguishable repre... read more
Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. However, previous approaches typically adopt a single-stage distillation par... read more
Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible synthesis, whil... read more
High-dimensional point cloud data arise across many scientific domains, especially single-cell biology. The shapes or topologies of these datasets determine the types of information that can be extracted. For example, clustered data supports cell-typ... read more
Postoperative recurrence (POR) is a major challenge in the long-term management of Crohn's disease (CD), affecting up to 70% of patients within the first year after surgical resection. The multifactorial pathogenesis of POR complicates prevention, wh... read more
Don't Miss the Future of Medicine
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.