Related papers: Beyond Conditional Computation: Retrieval-Augmente…

We propose a new perspective for approaching artificial general intelligence (AGI) through an intelligence foundation model (IFM). Unlike existing foundation models (FMs), which specialize in pattern learning within specific domains such as…

Foundation models, large-scale, pre-trained deep-learning models adapted to a wide range of downstream tasks have gained significant interest lately in various deep-learning problems undergoing a paradigm shift with the rise of these…

Deformable templates are essential to large-scale medical image registration, segmentation, and population analysis. Current conventional and deep network-based methods for template construction use only regularized registration objectives…

Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act as "words" that…

As memory increasingly dominates system cost and energy, heterogeneous on-chip memory systems that combine technologies with complementary characteristics are becoming essential. Gain Cell RAM (GCRAM) offers higher density, lower power, and…

Cardiac biosignals, such as electrocardiograms (ECG) and photoplethysmograms (PPG), are of paramount importance for the diagnosis, prevention, and management of cardiovascular diseases, and have been extensively used in a variety of…

Motivation: Sequence mapping is the cornerstone of modern genomics. However, most existing sequence mapping algorithms are insufficiently general. Results: We introduce context schemes: a method that allows the unambiguous recognition of a…

We present MEDUSA, an integrative method for learning motif models of transcription factor binding sites by incorporating promoter sequence and gene expression data. We use a modern large-margin machine learning approach, based on boosting,…

We challenge black-box purely deep neural approaches for molecules and graph generation, which are limited in controllability and lack formal guarantees. We introduce Neuro-Symbolic Graph Generative Modeling (NSGGM), a neurosymbolic…

Accurate molecular property prediction is central to drug discovery, catalysis, and process design, yet real-world applications are often limited by small datasets. Molecular foundation models provide a promising direction by learning…

While generative adversarial networks (GANs) have revolutionized machine learning, a number of open questions remain to fully understand them and exploit their power. One of these questions is how to efficiently achieve proper diversity and…

Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative approaches addressing the challenge belong to two broad categories, differing in how molecules are represented. One approach encodes molecular…

Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introduce noisy retrieval,…

The techniques of data-driven backmapping from coarse-grained (CG) to fine-grained (FG) representation often struggle with accuracy, unstable training, and physical realism, especially when applied to complex systems such as proteins. In…

The advancements in artificial intelligence in recent years, such as Large Language Models (LLMs), have fueled expectations for breakthroughs in genomic foundation models (GFMs). The code of nature, hidden in diverse genomes since the very…

We propose Deep Residual Mixture Models (DRMMs), a novel deep generative model architecture. Compared to other deep models, DRMMs allow more flexible conditional sampling: The model can be trained once with all variables, and then used for…

In the visual decoding domain, visually reconstructing presented images given the corresponding human brain activity monitored by functional magnetic resonance imaging (fMRI) is difficult, especially when reconstructing viewed natural…

Causal discovery, the task of inferring causal structure from data, has the potential to uncover mechanistic insights from biological experiments, especially those involving perturbations. However, causal discovery algorithms over larger…

Noninvasive reconstruction of cardiac transmembrane potential (TMP) from surface electrocardiograms (ECG) involves an ill-posed inverse problem. Model-constrained regularization is powerful for incorporating rich physiological knowledge…

$N$-gram language models (LM) have been largely superseded by neural LMs as the latter exhibits better performance. However, we find that $n$-gram models can achieve satisfactory performance on a large proportion of testing cases,…