Related papers: Optimizing optical potentials with physics-inspire…
Molecular dynamics simulations have emerged as a potent tool for investigating the physical properties and kinetic behaviors of materials at the atomic scale, particularly in extreme conditions. Ab initio accuracy is now achievable with…
Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local computation…
Achieving high-precision light manipulation is crucial for delivering information through complex media with high fidelity. However, existing spatial light modulation devices face a fundamental tradeoff between speed and accuracy. Digital…
Emerging artificial intelligence applications across the domains of computer vision, natural language processing, graph processing, and sequence prediction increasingly rely on deep neural networks (DNNs). These DNNs require significant…
This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, such as FPGAs, while maintaining high performance, accuracy,…
The reliability of artificial intelligence (AI) systems in open-world settings depends heavily on their ability to flag out-of-distribution (OOD) inputs unseen during training. Recent advances in large-scale vision-language models (VLMs)…
We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph…
Advanced microscopy and/or spectroscopy tools play indispensable role in nanoscience and nanotechnology research, as it provides rich information about the growth mechanism, chemical compositions, crystallography, and other important…
The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and…
This paper introduces a new method of data-driven microscope design for virtual fluorescence microscopy. Our results show that by including a model of illumination within the first layers of a deep convolutional neural network, it is…
On-chip integration of highly anisotropic two-dimensional (2D) materials offers new opportunities for realizing high performance polarization selective devices. Obtaining optimized designs for such devices requires extensively sweeping…
While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…
In traditional topology optimization, the computing time required to iteratively update the material distribution within a design domain strongly depends on the complexity or size of the problem, limiting its application in real engineering…
How can one design complex systems capable of learning for a given functionality? In the context of ultrafast laser-surface interaction, we unravel the nature of learning schemes tied to the emergence of complexity in dissipative…
Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based acceleration methods often face significant image quality…
We study a class of misspecified saddle point (SP) problems, where the optimization objective depends on an unknown parameter that must be learned concurrently from data. Unlike existing studies that assume parameters are fully known or…
High Power Laser (HPL) systems operate in the attoseconds regime -- the shortest timescale ever created by humanity. HPL systems are instrumental in high-energy physics, leveraging ultra-short impulse durations to yield extremely high…
Optical neural networks (ONNs) perform extensive computations using photons instead of electrons, resulting in passively energy-efficient and low-latency computing. Among various ONNs, the diffractive optical neural networks (DONNs)…
This paper explores how deep learning techniques can improve visual-based SLAM performance in challenging environments. By combining deep feature extraction and deep matching methods, we introduce a versatile hybrid visual SLAM system…
Predict-then-Optimize (PTO) pipelines are widely employed in computing and networked systems, where Machine Learning (ML) models are used to predict critical contextual information for downstream decision-making tasks such as cloud LLM…