arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Kay Chen
Computer Science > Artificial Intelligence
Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new paradigm that turns iterative algorithms into trainable models.
Computer Science > Sound
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Quantitative Biology > Neurons and Cognition
Stimulus-driven auditory attention determines which sound gains priority when multiple sources compete without an explicit listening goal, yet most computational studies focus either on acoustic salience or on decoding predefined attended targets.
Computer Science > Neural and Evolutionary Computing
Large language models (LLMs) enable automated algorithm design (AAD) through reasoning and code synthesis. However, most existing LLM-based AAD methods separate algorithm design from target optimization, deploying a fixed design even as the optimization state evolves. Conventional adaptive optimizers can respond to such changes, but their adjustments remain confined to predefined parameters, operators, or strategies.
Computer Science > Artificial Intelligence
As evolutionary transfer optimization (ETO) scales to larger collections of related tasks, problem evaluation can become a major source of runtime growth. This work studies problem-side evaluation scaling in task-parameterized applications and reformulates application-specific serial computations into forms suitable for parallel execution.
Computer Science > Artificial Intelligence
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Computer Science > Multiagent Systems
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2512.11453] Learning to Evolve with Convergence Guarantee via Neural Unrolling
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
scKAN: interpretable single-cell analysis for cell-type-specific gene discovery and drug repurposing via Kolmogorov-Arnold networks - Genome Biology
The architecture of KAN [22] leverages the Kolmogorov-Arnold representation theorem, which states that any continuous multivariate function \(f\) can be represented as a composition of a finite number of continuous univariate functions: $$f\left(x\right)=f\left({x}_{1},\cdots ,{x}_{n}\right)=\sum_{q=0}^{2n}{\Phi }_{q}\left(\sum_{p=1}^{n}{\phi }_{q,p}\left({x}_{p}\right)\right)$$ (1) where \({\phi }_{q,p}:[\text{0,1}]\to {\mathbb{R}},{\Phi }_{q}:{\mathbb{R}}\to {\mathbb{R}}\).
A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving
[2408.11330] Design Principle Transfer in Neural Architecture Search via Large Language Models
Coming this September, the Forum is free, virtual, and open to all. Sign Up and Learn more.
[2408.07176] Surrogate-Assisted Search with Competitive Knowledge Transfer for Expensive Optimization
Coming this September, the Forum is free, virtual, and open to all. Sign Up and Learn more.
[2406.08987] Autonomous Multi-Objective Optimization Using Large Language Model
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2405.05767] Large Language Model-Aided Evolutionary Search for Constrained Multiobjective Optimization
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap
[Submitted on 18 Jan 2024 ( v1 ), last revised 7 Feb 2024 (this version, v2)] Title:Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap Download a PDF of the paper titled Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap, by Xingyu Wu and 4 other authors Download PDF Abstract:Large Language Models (LLMs) have not only revolutionized natural language processing but also extended their prowess to various domains, marking a significant...
[2312.06125] Enhancing Generalization and Scalability for Multi-Objective Optimization with Population Pre-Training
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation
[Submitted on 22 Nov 2023 ( v1 ), last revised 16 May 2024 (this version, v3)] Title:Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation View a PDF of the paper titled Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation, by Xingyu Wu and 4 other authors View PDF HTML (experimental) Abstract:Algorithm selection, a critical process of automated machine learning, aims to identify the most suitable...
[2310.12538] Solving Expensive Optimization Problems in Dynamic Environments with Meta-learning
Free, fully remote and open to all. Because science is only open if it is accessible. Learn more. Because without accessibility Open Science is not truly open
[2308.15150] Unleashing the Potential of Spiking Neural Networks for Sequential Modeling with Contextual Embedding
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2307.07231] Long Short-term Memory with Two-Compartment Spiking Neuron
arXiv:2307.07231 (cs) Download a PDF of the paper titled Long Short-term Memory with Two-Compartment Spiking Neuron, by Shimin Zhang and 5 other authors Download PDF Submission history From: Qu Yang [ view email] [v1] Fri, 14 Jul 2023 08:51:03 UTC (510 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Links to Code Toggle CatalyzeX Code...
SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2305.16594] A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks
[Submitted on 26 May 2023 ( v1 ), last revised 4 Jan 2024 (this version, v2)] Title:A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks Download a PDF of the paper titled A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks, by Xinyi Chen and 4 other authors Download PDF HTML (experimental) Abstract:Recently, brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Kay
Contact Kay, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack