Artificial Intelligence Medical Compendium

Recent large vision-language models (VLMs) pair a visual encoder with a large language model (LLM) and perform well on diverse image-text tasks, yet their reliability is often limited by decoder attention pathologies that suppress visual evidence and... read more 

Causal video diffusion models generate video autoregressively, which suits streaming, interactive, and long-video generation. Under standard training, however, they often yield lower generation quality than bidirectional models of the same size. Many... read more 

Visual instance retrieval often fails when the same object appears at different apparent sizes in the query and gallery. We show that the dominant cause is usually not resolution loss but object-to-image (O2I) ratio mismatch: the object occupies diff... read more 

Spiking neural networks (SNNs) offer an energy-efficient computing paradigm through sparse event-driven computation, showing great potential for efficient multimodal learning. However, applying SNNs to high-level multimodal tasks, such as image-text ... read more 

DNNs exhibit robustness and generalisation issues not seen in humans. They are also far less data-efficient learners, requiring considerably more training samples to accurately classify novel exemplars. Inductive bias could help with these issues by ... read more 

Parallel magnetic resonance imaging reconstruction is an ill-posed inverse problem under undersampling. Multi-coil acquisition and Hankel lifting expose complementary repeated information: observations of the same anatomy across coils and repeated lo... read more 

Adapting a pre-trained 3D Gaussian Splatting (3DGS) road scene to a new time of day requires learning appearance changes from a few anchor images while preserving consistent, real-time rendering. We propose PAM-ToD, a lightweight plug-in that learns ... read more 

End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artificial neural network (ANN) planners meet the accuracy requirement at the cost of heavy dense computati... read more 

To test conditional independence of $X$ and $Y$ given a text or an image $Z$, one conditions on an embedding $ψ(Z)$ in place of $Z$. The embedded test is valid if $Z$ is independent of $X$ or of $Y$ given $ψ(Z)$, which cannot be confirmed from data, ... read more 

Cross-view geo-localization (CVGL) aims to estimate geographic locations by matching images captured from different viewpoints, such as drone and satellite views. Existing methods mainly rely on visual representations, but often fail to jointly model... read more