Designing neuromorphic sensory processing units (NSPUs) based on Temporal Neural Networks (TNNs) is a highly challenging task due to the reliance on manual, labor-intensive hardware development processes. TNNs have been identified as highly promising for real-time edge AI applications, mainly because they are energy-efficient and bio-inspired. However, available methodologies lack automation and are not very… →

Artificial Life (ALife) research explores the emergence of lifelike behaviors through computational simulations, providing a unique framework to study “life as it could be.” However, the field faces significant limitations: a reliance on manually crafted simulation rules and configurations. This process is time-intensive and constrained by human intuition, leaving many potential discoveries unexplored. Researchers often… →

Deploying Deep Neural Networks (DNNs) on edge devices, such as smartphones and autonomous vehicles, remains a significant challenge due to their computationally intensive nature.  Most existing pruning algorithms struggle to balance high compression rates and inference accuracy and have to be compatible with commercial hardware—unstructured pruning yields irregular sparsity that often limits its usage in… →

A direct correlation exists between an LLM’s training corpus quality and its capabilities. Consequently, researchers have invested a great deal of effort into curating extensive, high-quality datasets, which, at present, are achievable with craftful human annotations. Man-made datasets, however, have one downside: their reliance becomes increasingly unsustainable as complexity grows.  Many methods have been worked… →

Researchers are focusing increasingly on creating systems that can handle multi-modal data exploration, which combines structured and unstructured data. This involves analyzing text, images, videos, and databases to answer complex queries. These capabilities are crucial in healthcare, where medical professionals interact with patient records, medical imaging, and textual reports. Similarly, multi-modal exploration helps interpret databases… →

LLMs have revolutionized software development by automating coding tasks and bridging the natural language and programming gap. While highly effective for general-purpose programming, they struggle with specialized domains like High-Performance Computing (HPC), particularly in generating parallel code. This limitation arises from the scarcity of high-quality parallel code data in pre-training datasets and the inherent complexity… →

Large Language Models (LLMs) have shown significant potential in reasoning tasks, using methods like Chain-of-Thought (CoT) to break down complex problems into manageable steps. However, this capability comes with challenges. CoT prompts often increase token usage, leading to higher computational costs and energy consumption. This inefficiency is a concern for applications that require both precision… →

The development of Transformer models has significantly advanced artificial intelligence, delivering remarkable performance across diverse tasks. However, these advancements often come with steep computational requirements, presenting challenges in scalability and efficiency. Sparsely activated Mixture-of-Experts (MoE) architectures provide a promising solution, enabling increased model capacity without proportional computational costs. Yet, traditional TopK+Softmax routing in MoE models… →

Operator learning is a transformative approach in scientific computing. It focuses on developing models that map functions to other functions, an essential aspect of solving partial differential equations (PDEs). Unlike traditional neural network tasks, these mappings operate in infinite-dimensional spaces, making them particularly suitable for scientific domains where real-world problems inherently exist in expansive mathematical… →