Related papers: Fast Reconstruction of Compact Context-Specific Me…
Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes. Few-shot…
Beyond the Transformer, it is important to explore how to exploit the capacity of the MetaFormer, an architecture that is fundamental to the performance improvements of the Transformer. Previous studies have exploited it only for the…
Man-made environments typically comprise planar structures that exhibit numerous geometric relationships, such as parallelism, coplanarity, and orthogonality. Making full use of these relationships can considerably improve the robustness of…
Accurately determining and classifying the structure of complex networks is the focus of much current research. One class of network of particular interest are metabolic pathways, which have previously been studied from a graph theoretical…
In this work we propose a novel algorithmic strategy that allows for an efficient characterization of the whole set of stable fluxes compatible with the metabolic constraints. The algorithm, based on the well-known Bethe approximation,…
One of the defining features of living systems is their adaptability to changing environmental conditions. This requires organisms to extract temporal and spatial features of their environment, and use that information to compute the…
Context matters! Nevertheless, there has not been much research in exploiting contextual information in deep neural networks. For most part, the entire usage of contextual information has been limited to recurrent neural networks. Attention…
Parallel imaging, a fast MRI technique, involves dynamic adjustments based on the configuration i.e. number, positioning, and sensitivity of the coils with respect to the anatomy under study. Conventional deep learning-based image…
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…
Cellular phenotypes are determined by the dynamical activity of networks of co-regulated genes. Elucidating such networks is crucial for the understanding of normal cell physiology as well as for the dissection of complex pathologic…
Metabolism is a fascinating cell machinery underlying life and disease and genome-scale reconstructions provide us with a captivating view of its complexity. However, deciphering the relationship between metabolic structure and function…
We study the network reconstruction problem for an epidemic reaction-diffusion. These models are an extension of deterministic, compartmental models to a graph setting, where the reactions within the nodes are coupled by a diffusion. We…
High-throughput techniques are leading to an explosive growth in the size of biological databases and creating the opportunity to revolutionize our understanding of life and disease. Interpretation of these data remains, however, a major…
Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…
Reconstructing complex networks from measurable data is a fundamental problem for understanding and controlling collective dynamics of complex networked systems. However, a significant challenge arises when we attempt to decode structural…
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the…
The reconstruction of event-level information, such as the direction or energy of a neutrino interacting in IceCube DeepCore, is a crucial ingredient to many physics analyses. Algorithms to extract this high level information from the…
Context plays a crucial role in visual recognition as it provides complementary clues for different learning tasks including image classification and annotation. As the performances of these tasks are currently reaching a plateau, any extra…
Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context length. However, their potential is limited by the next-token…
Metabolic networks consist of linked functional components, or modules. The mechanism underlying metabolic network modularity is of great interest not only to researchers of basic science but also to those in fields of engineering. Previous…