检索结果-内蒙古大学图书馆

Large Scale Multi-Task Bayesian Optimization with Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zeng, Yimeng Maus, Natalie Jones, Haydn Thomas Tao, Jeffrey Wan, Fangping Torres, Marcelo Der Torossian de la Fuente-Nunez, Cesar Marcus, Ryan Bastani, Osbert Gardner, Jacob R. Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA United States Machine Biology Group Departments of Psychiatry and Microbiology Institute for Biomedical Informatics Institute for Translational Medicine and Therapeutics Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Departments of Bioengineering and Chemical and Biomolecular Engineering School of Engineering and Applied Science University of Pennsylvania PhiladelphiaPA United States Department of Chemistry School of Arts and Sciences University of Pennsylvania PhiladelphiaPA United States Penn Institute for Computational Science University of Pennsylvania PhiladelphiaPA United States

In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling to more than a moderate number of tasks. We introduce a novel approach leveraging large language models (LLMs) to learn from, and improve upon, previous optimization trajectories, scaling to approximately 2000 distinct tasks. Specifically, we propose an iterative framework in which an LLM is fine-tuned using the high quality solutions produced by BayesOpt to generate improved initializations that accelerate convergence for future optimization tasks based on previous search trajectories. We evaluate our method on two distinct domains: database query optimization and antimicrobial peptide design. Results demonstrate that our approach creates a positive feedback loop, where the LLM’s generated initializations gradually improve, leading to better optimization performance. As this feedback loop continues, we find that the LLM is eventually able to generate solutions to new tasks in just a few shots that are better than the solutions produced by "from scratch" by Bayesian optimization while simultaneously requiring significantly fewer oracle calls. © 2025, CC BY-SA.

关键词： Structured Query Language

Attention-Based Functional-Group Coarse-Graining: A Deep Learning Framework for Molecular Prediction and Design

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Han, Ming Sun, Ge de Pablo, Juan J. Pritzker School of Molecular Engineering University of Chicago ChicagoIL United States James Franck Institute University of Chicago ChicagoIL United States Department of Chemical and Biomolecular Engineering Tandon School of Engineering New York University BrooklynNY United States Department of Computer Science Courant Institute of Mathematical Sciences New York University New YorkNY United States Department of Physics New York University New YorkNY United States Materials Science Division Argonne National Laboratory LemontIL United States

Machine learning (ML) offers considerable promise for the design of new molecules and materials. In real-world applications, the design problem is often domain-specific, and suffers from insufficient data, particularly labeled data, for ML training. In this study, we report a data-efficient, deep-learning framework for molecular discovery that integrates a coarse-grained functional-group representation with a self-attention mechanism to capture intricate chemical interactions. Our approach exploits group-contribution theory to create a graph-based intermediate representation of molecules, serving as a low-dimensional embedding that substantially reduces the data demands typically required for training. By leveraging the self-attention mechanism to learn subtle chemical context, our method consistently outperforms conventional methods in predicting multiple thermophysical properties. In a case study focused on adhesive polymer monomers, we train on a limited dataset comprising just 6,000 unlabeled and 600 labeled monomers. The resulting chemistry prediction model achieves over 92% accuracy in forecasting properties directly from SMILES strings, exceeding the performance of current state-of-the-art techniques. Furthermore, the latent molecular embedding is invertible, allowing the design pipeline to incorporate a decoder that can automatically generate new monomers from the learned chemical subspace. We illustrate this functionality by targeting high and low glass transition temperatures (Tg), successfully identifying novel candidates whose Tg extends beyond the range observed in the training data. The ease with which our coarse-grained, attention-based framework navigates both chemical diversity and data scarcity offers a compelling route to accelerate and broaden the search for functional materials. Copyright © 2025, The Authors. All rights reserved.

关键词： Adhesives

Modular HfOx-RRAM for On-Demand Micromodular Electronics

学校读者我要写书评

暂无评论

IEEE Electron Device Letters

IEEE Electron Device Letters 2025年

作者： Kurup, Siddharth Bhattacharya, Swagat Banner, Rebecca K. Yue, Kaifan Ayyappan, Praveen Raj Aziz, Daniel Elly, Hubert N. Barton, Kira L. Hasler, Jennifer Filler, Michael A. Vogel, Eric M. Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA30332 United States Georgia Institute of Technology School of Materials Science and Engineering AtlantaGA30332 United States University of Michigan Department of Robotics Ann ArborMI48109 United States Georgia Institute of Technology School of Chemical and Biomolecular Engineering AtlantaGA30332 United States University of Michigan Department of Mechanical Engineering Ann ArborMI48109 United States

Micromodular metal-HfOx-metal resistive random-access memories (RRAM) were fabricated, transferred to foreign substrates, and contacted using high-resolution electrohydrodynamic jet (e-jet) printing. The modular RRAM exhibited bipolar switching at low operating voltages and multi-level analog resistance states programmable using variable amplitude voltage pulses. These variable resistance RRAMs were also integrated with an amplifier and a bandpass filter to modulate their gain and corner frequencies. This work enables integration of high-quality RRAM devices in modular circuits and paves the way for microscale heterogeneous integration at the device level. © 1980-2012 IEEE.

关键词： RRAM

Gentlest ascent dynamics on manifolds defined by adaptively sampled point-clouds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bello-Rivas, Juan M. Georgiou, Anastasia Vandecasteele, Hannes Kevrekidis, Ioannis G. Department of Chemical and Biomolecular Engineering Whiting School of Engineering Johns Hopkins University 3400 North Charles Street BaltimoreMD21218 United States Department of Computer Science KU Leuven Celestijnenlaan 200A Leuven3001 Belgium Departments of Applied Mathematics and Statistics Johns Hopkins University 3400 North Charles Street BaltimoreMD21218 United States

Finding saddle points of dynamical systems is an important problem in practical applications such as the study of rare events of molecular systems. Gentlest ascent dynamics (GAD)1 is one of a number of algorithms in existence that attempt to find saddle points in dynamical systems. It works by deriving a new dynamical system in which saddle points of the original system become stable equilibria. GAD has been recently generalized to the study of dynamical systems on manifolds (differential algebraic equations) described by equality constraints2 and given in an extrinsic formulation. In this paper, we present an extension of GAD to manifolds defined by point-clouds, formulated using the intrinsic viewpoint. These point-clouds are adaptively sampled during an iterative process that drives the system from the initial conformation (typically in the neighborhood of a stable equilibrium) to a saddle point. Our method requires the reactant (initial conformation), does not require the explicit constraint equations to be specified, and is purely data-driven. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamical systems

Semi-Siamese Network for Robust Change Detection Across Different Domains with Applications to 3D Printing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Niu, Yushuo Chadwick, Ethan Ma, Anson W.K. Yang, Qian Computer Science & Engineering Department University of Connecticut 371 Fairfield Way Unit 4155 StorrsCT06269-4155 United States Chemical & Biomolecular Engineering Department University of Connecticut 97 North Eagleville Road Unit 3136 StorrsCT06269-3136 United States

Automatic defect detection for 3D printing processes, which shares many characteristics with change detection problems, is a vital step for quality control of 3D printed products. However, there are some critical challenges in the current state of practice. First, existing methods for computer vision-based process monitoring typically work well only under specific camera viewpoints and lighting situations, requiring expensive pre-processing, alignment, and camera setups. Second, many defect detection techniques are specific to pre-defined defect patterns and/or print schematics. In this work, we approach the defect detection problem using a novel Semi-Siamese deep learning model that directly compares a reference schematic of the desired print and a camera image of the achieved print. The model then solves an image segmentation problem, precisely identifying the locations of defects of different types with respect to the reference schematic. Our model is designed to enable comparison of heterogeneous images from different domains while being robust against perturbations in the imaging setup such as different camera angles and illumination. Crucially, we show that our simple architecture, which is easy to pre-train for enhanced performance on new datasets, outperforms more complex state-of-the-art approaches based on generative adversarial networks and transformers. Using our model, defect localization predictions can be made in less than half a second per layer using a standard MacBook Pro while achieving an F1-score of more than 0.9, demonstrating the efficacy of using our method for in-situ defect detection in 3D printing. © 2022, CC BY-NC-SA.

关键词： 3D printing

High contrast reporter cleavage detection for enhancing porous silicon sensor sensitivity

学校读者我要写书评

暂无评论

High contrast reporter cleavage detection for enhancing poro...

CLEO: QELS_Fundamental science, CLEO: QELS 2021 - Part of Conference on Lasers and Electro-Optics, CLEO 2021

作者： Layouni, Rabeb Dubrovsky, Michael Bao, Mengdi Chung, Haejun Du, Ke Boriskina, Svetlana V. Weiss, Sharon M. Vermeulen, And Diedrik Department of Chemical and Biomolecular Engineering Department of Electrical Engineering and Computer Science Vanderbilt University NashvilleTN37235 United States SiPhox Inc. 325 Vassar Street CambridgeMA02139 United States Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Department of Mechanical Engineering Rochester Institute of Technology RochesterNY14623 United States

We show the first experimental implementation of biosensing using high contrast reporter cleavage detection (HCRCD). HCRCD makes use of dramatic signal amplification caused by cleavage of high-contrast nanoparticle la... 详细信息

ISBN: (纸本)9781557528209

关键词： Porous silicon

A Novel In-situ Method for Measuring Soil Organic Carbon Using Photoacoustic Sensor

学校读者我要写书评

暂无评论

A Novel In-situ Method for Measuring Soil Organic Carbon Usi...

IEEE SENSORS

作者： Md Faishal Yousuf MD Shaad Mahmud Baikun Li Yu Lei Haiying Tao Department of Electrical and Computer Engineering University of New Hampshire Durham NH USA Department of Civil and Environmental Engineering University of Connecticut Storrs CT USA Department of Chemical and Biomolecular Engineering University of Connecticut Storrs CT USA Department of Plant Science and Landscape Architecture University of Connecticut Storrs CT USA

ISBN: (数字)9781665484640

ISBN: (纸本)9781665484657

Organic and inorganic elements of soil exhibit a wide range of physical and chemical characteristics. Exact soil composition estimates are required for many ecological and soil science studies and global climate change research. The most typical method for estimating soil variables involves collecting and analyzing data in a laboratory, which is time-consuming and expensive. This paper proposes a rapid, in-situ approach for assessing soil organic carbon utilizing the soil combustion method. In the suggested approach, a metal tube with a heating probe heats the soil to approximately 400°C. The heat oxidizes a known-volume soil sample, creating CO 2 • To estimate soil organic carbon, a CO 2 sensor measures the accumulated CO 2 concentration at the tube's top. A laboratory experiment was undertaken to demonstrate the proposed method's potential.

关键词： Heating systems Soil measurements Moisture Metals Soil Combustion Sensors

Morphological imaging of 3D cultured kidney mesangial cells using gradient light interference microscopy

学校读者我要写书评

暂无评论

Morphological imaging of 3D cultured kidney mesangial cells ...

Digital Holography and Three-Dimensional Imaging, DH 2024

作者： Butola, Ankit Ghosh, Biswajoy Park, Jaena Kwon, Minsung De la Cadena, Alejandro Mukherjee, Sudipta Bhargava, Rohit Boppart, Stephen A. Agarwal, Krishna Department of Physics and Technology UiT The Arctic University of Norway Tromsø9037 Norway 405 N. Mathews Ave. UrbanaIL61801 United States Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign 405 N Mathews Avenue UrbanaIL61801 United States Department of Bioengineering University of Illinois at Urbana-Champaign 1406 W Green Street UrbanaIL61801 United States Department of Chemical and Biomolecular Engineering University of Illinois Urbana-Champaign UrbanaIL United States Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL United States Cancer Center at Illinois University of Illinois Urbana-Champaign UrbanaIL United States Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign 306 N Wright Street UrbanaIL61801 United States Carle Illinois College of Medicine University of Illinois at Urbana-Champaign 506 S Mathews Avenue UrbanaIL61801 United States

We present a gradient light interference microscopy system to visualize 3D quantitative imaging of kidney mesangial cells. We used the system to obtain the morphology of 3D cultured kidney cells of thickness 200 µ... 详细信息

关键词： Light interference

(F₅PhO)₂-F₁₆-SiPc as an air-stable, high-performance n-type semiconductor with poor cannabinoid sensing capabilities

学校读者我要写书评

暂无评论

RSC Applied Interfaces

RSC Applied Interfaces 2024年第6期1卷 1222-1232页

作者： Lamontagne, Halynne R. Cyr, Mélanie Vebber, Mário C. Swaraj, Sufal Harris, Cory S. Brusso, Jaclyn L. Shuhendler, Adam J. Lessard, Benoît H. Department of Chemical and Biological Engineering University of Ottawa 161 Louis Pasteur Ottawa K1N 6N5 ON Canada Department of Chemistry and Biomolecular Sciences University of Ottawa 150 Louis Pasteur Ottawa K1N 6N5 ON Canada SOLEIL L'Orme des Merisiers Départementale 128 Saint-Aubin 91190 France Department of Biology University of Ottawa 30 Marie Curie Ottawa K1N 6N5 ON Canada University of Ottawa Heart Institute 40 Ruskin St Ottawa K1Y 4W7 ON Canada School of Electrical Engineering and Computer Science University of Ottawa 800 King Edward Ave Ottawa K1N 6N5 ON Canada

Organic thin-film transistors (OTFTs) are an emerging platform for rapid, point-of-source detection and speciation of Δ9-tetrahydrocannabinol (THC) and cannabidiol (CBD). (F5PhO)2-F16-SiPc semiconductor was implement...

Organic thin-film transistors (OTFTs) are an emerging platform for rapid, point-of-source detection and speciation of Δ⁹-tetrahydrocannabinol (THC) and cannabidiol (CBD). (F₅PhO)₂-F₁₆-SiPc semiconductor was implemented into high performance, air-stable n-type bottom gate, bottom contact OTFTs, however, the resulting device performance changes in response to THC and CBD were negligible. We explored the orientation of the corresponding thin films by synchrotron-based grazing incidence wide-angle X-ray scattering (GIWAXS) and angle-dependent near-edge X-ray absorption fine structure (NEXAFS), as well as polarized Raman microscopy. These techniques demonstrate for the first time that (F₅PhO)₂-F₁₆-SiPc molecules are at a 45-48° orientation to the substrate;comparable to other reported R₂-SiPcs. This orientation did not change upon exposure to THC and CBD, which has previously been reported for phthalocyanine-based OTFT cannabinoid sensors. The presence of two bulky axial groups, along with the absence of hydrogens in the molecule and the low reactivity of the silicon atom likely causes the lack of interaction with the cannabinoids. While (F₅PhO)₂-F₁₆-SiPc may be a successfully air-stable n-type semiconductor for OTFTs, the structural changes performed to make it air stable over traditional non-fluorinated silicon MPcs, are likely responsible for its lack of response to cannabinoid exposure. © 2024 RSC.

关键词：