Related papers: LightRidge: An End-to-end Agile Design Framework f…
Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…
Over the past few years, neural network methods have evolved in various directions for approximating partial differential equations (PDEs). A promising new development is the integration of neural networks with classical numerical…
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions. However, these simulations are non-differentiable, forcing…
Thanks to their universal approximation properties and new efficient training strategies, Deep Neural Networks are becoming a valuable tool for the approximation of mathematical operators. In the present work, we introduce Mesh-Informed…
Diffusion models demonstrate remarkable capabilities in capturing complex data distributions and have achieved compelling results in many generative tasks. While they have recently been extended to dense prediction tasks such as depth…
Nonlinear computation is essential for a wide range of information processing tasks, yet implementing nonlinear functions using optical systems remains a challenge due to the weak and power-intensive nature of optical nonlinearities.…
Physics-Informed Neural Networks (PINNs) seek to solve partial differential equations (PDEs) with deep learning. Mainstream approaches that deploy fully-connected multi-layer deep learning architectures require prolonged training to achieve…
The numerical solution of differential equations using neural networks has become a central topic in scientific computing, with Physics-Informed Neural Networks (PINNs) emerging as a powerful paradigm for both forward and inverse problems.…
Artificial neural networks have revolutionized fields from computer vision to natural language processing, yet their growing energy and computational demands threaten future progress. Optical neural networks promise greater speed,…
Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed…
Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize…
Compact photonic elements that control both the diffraction and interference of light offer superior performance at ultra-compact dimensions. Unlike conventional optical structures, these diffractive optical elements can provide…
Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…
This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…
The revolution in materials in the past century was built on a knowledge of the atomic arrangements and the structure-property relationship. The sine qua non for obtaining quantitative structural information is single crystal…
The present research aims to provide a practical numerical tool for the mechanical analysis of nanoscale trusses with similar accuracy to molecular dynamics (MD). As a first step, MD simulations of uniaxial tensile and compression tests of…
The rapid scaling of deep neural networks comes at the cost of unsustainable power consumption. While optical neural networks offer an alternative, their capabilities remain constrained by the lack of efficient optical nonlinearities. To…
Deep hedging represents a cutting-edge approach to risk management for financial derivatives by leveraging the power of deep learning. However, existing methods often face challenges related to computational inefficiency, sensitivity to…
Optical neural networks (ONNs), or optical neuromorphic hardware accelerators, have the potential to dramatically enhance the computing power and energy efficiency of mainstream electronic processors, due to their ultralarge bandwidths of…
With the rapid advancement of deep learning, the field of change detection (CD) in remote sensing imagery has achieved remarkable progress. Existing change detection methods primarily focus on achieving higher accuracy with increased…