Related papers: Optimal transport unlocks end-to-end learning for …
Advanced microscopy techniques are essential in biomedical research for visualising and tracking biomolecules within living cells and their compartments. Conventional fluorescence microscopy methods, however, often struggle with accurately…
Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Draft Speculative Decoding (MDSD) is a recent approach where,…
Super-resolution microscopy is rapidly gaining importance as an analytical tool in the life sciences. A compelling feature is the ability to label biological units of interest with fluorescent markers in living cells and to observe them…
Super-resolution microscopy normally requiring complex and cumbersome optics is not applicable for in situ imaging through a narrow channel. Here, we demonstrate single hair-thin multimode fiber (MMF) endoscope (less than 250 ${\mu}m$) for…
We present a novel spectral learning algorithm for simultaneous localization and mapping (SLAM) from range data with known correspondences. This algorithm is an instance of a general spectral system identification framework, from which it…
We study an inverse problem for Light Sheet Fluorescence Microscopy (LSFM), where the density of fluorescent molecules needs to be reconstructed. Our first step is to present a mathematical model to describe the measurements obtained by an…
Simultaneous Localization and Mapping (SLAM) algorithms perform visual-inertial estimation via filtering or batch optimization methods. Empirical evidence suggests that filtering algorithms are computationally faster, while optimization…
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…
Fast and accurate object perception in low-light traffic scenes has attracted increasing attention. However, due to severe illumination degradation and the lack of reliable visual cues, existing perception models and methods struggle to…
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has long been suffering from fragmentary object regions led by Class Activation Map (CAM), which is incapable of generating fine-grained masks for semantic segmentation.…
Free-form strong-lensing (SL) mass reconstructions typically suffer from overfitting, which manifest itself as false-positive small-scale fluctuations. We present a new free-form MAximum-entropy ReconStruction (${\tt MARS}$) method without…
Recent segmentation methods leveraging Multi-modal Large Language Models (MLLMs) have shown reliable object-level segmentation and enhanced spatial perception. However, almost all previous methods predominantly rely on specialist mask…
Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning. However, existing methods either not explicitly learn the transport map or do not support general cost function. In this…
Structured illumination microscopy (SIM) has become an important technique for optical super-resolution imaging because it allows a doubling of image resolution at speeds compatible for live-cell imaging. However, the reconstruction of SIM…
We propose a continuous non-convex variational model for Single Molecule Localisation Microscopy (SMLM) super-resolution in order to overcome light diffraction barriers. Namely, we consider a variation of the Continuous Exact $\ell_0$…
Live-cell imaging of multiple subcellular structures is essential for understanding subcellular dynamics. However, the conventional multi-color sequential fluorescence microscopy suffers from significant imaging delays and limited number of…
Brain pathologies often manifest as partial or complete loss of tissue. The goal of many neuroimaging studies is to capture the location and amount of tissue changes with respect to a clinical variable of interest, such as disease…
Fast 3D super-resolution imaging is essential for decoding rapidly occurring biological processes. Encoding single molecules to their respective planes enable simultaneous multi-plane super-resolution volume imaging. This saves the…
Space-division multiplexing is a promising technology in optical fibre communication to improve the transmission capacity of a single optical fibre. However, the number of channels that can be multiplexed is limited by the crosstalks…
Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…