The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can the semantic knowledge of a language model efficiently improve a visio... read more
Real-world image restoration is challenging due to complex and interacting mixed degradations. Recent agent-based approaches address this problem by composing multiple task-specific restoration tools. However, empirical analysis reveals that their pe... read more
Accurate modeling of aerodynamic loads is essential for understanding and predicting the responses of complex structural systems. However, these models often rely on simplifications of the true physical forces, introducing assumptions that can limit ... read more
Magnetic resonance imaging (MRI) is highly susceptible to patient motion due to its relatively long acquisition times and the fact that data are acquired sequentially in k-space. Even small patient movements introduce phase inconsistencies across mea... read more
In everyday photography, aesthetically appealing moments are often captured with structural flaws (e.g., composition, camera viewpoint, or pose) that existing retouching and portrait enhancement methods cannot fix. We formulate Aesthetic Photo Recons... read more
Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In this work, we... read more
Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensitivity of conventional cameras. In this work, we explore gait recognition using event cameras, whic... read more
High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly diffusion models... read more
Symbolic methods are generally not considered competitive with strong modern learners on realistic supervised tasks. We evaluate Algebraic Machine Learning (AML), a framework that learns through subdirect decomposition of algebraic structure rather t... read more
Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking the essential global illumination in images and the inherent noise sensitivity of event signals in ... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.