中文
相关论文

相关论文: WfChef: Automated Generation of Accurate Scientifi…

200 篇论文

Experimental science is enabled by the combination of synthesis, imaging, and functional characterization. Synthesis of a new material is typically followed by a set of characterization methods aiming to provide feedback for optimization or…

Scientific writing is a challenging task, particularly for novice researchers who often rely on feedback from experienced peers. Recent work has primarily focused on improving surface form and style rather than manuscript content. In this…

计算与语言 · 计算机科学 2024-06-05 Eric Chamoun , Michael Schlichktrull , Andreas Vlachos

Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…

人工智能 · 计算机科学 2026-04-16 Qibin Liu , Julia Gonski

Current publicly available knowledge work data collections lack diversity, extensive annotations, and contextual information about the users and their documents. These issues hinder objective and comparable data-driven evaluations and…

人工智能 · 计算机科学 2024-10-25 Desiree Heim , Christian Jilek , Adrian Ulges , Andreas Dengel

Generative modeling has been used frequently in synthetic data generation. Fairness and privacy are two big concerns for synthetic data. Although Recent GAN [\cite{goodfellow2014generative}] based methods show good results in preserving…

机器学习 · 计算机科学 2023-07-04 Weijie Xu , Jinjin Zhao , Francis Iannacci , Bo Wang

Programming is essential to modern scientific research, yet most scientists report inadequate training for the software development their work demands. Generative AI tools capable of code generation may support scientific programmers, but…

软件工程 · 计算机科学 2026-04-13 Gabrielle O'Brien , Alexis Parker , Nasir Eisty , Jeffrey Carver

Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access…

人工智能 · 计算机科学 2026-04-01 Jaewoong Lee , Taeun Bae , Jihan Kim

GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…

人工智能 · 计算机科学 2026-05-15 Drewry H. Morris , Luis Valles , Reza Hosseini Ghomi

Among various aspects of ensuring the responsible design of AI tools for healthcare applications, addressing fairness concerns has been a key focus area. Specifically, given the wide spread of electronic health record (EHR) data and their…

机器学习 · 计算机科学 2025-06-30 Mirza Farhan Bin Tarek , Raphael Poulain , Rahmatollah Beheshti

Progress in science is deeply bound to the effective use of high-performance computing infrastructures and to the efficient extraction of knowledge from vast amounts of data. Such data comes from different sources that follow a cycle…

分布式、并行与集群计算 · 计算机科学 2020-06-15 Rosa M Badia , Jorge Ejarque , Francesc Lordan , Daniele Lezzi , Javier Conejero , Javier Álvarez Cid-Fuentes , Yolanda Becerra , Anna Queralt

We develop the first theory of control-flow graphs from first principles, and use it to create an algorithm for automatically synthesizing many variants of control-flow graph generators from a language's operational semantics. Our approach…

编程语言 · 计算机科学 2022-07-25 James Koppel , Jackson Kearl , Armando Solar-Lezama

Scientific workflows are becoming increasingly popular for compute-intensive and data-intensive scientific applications. The vision and promise of scientific workflows includes rapid, easy workflow design, reuse, scalable execution, and…

数据库 · 计算机科学 2013-11-26 Víctor Cuevas-Vicenttín , Saumen Dey , Sven Köhler , Sean Riddle , Bertram Ludäscher

Generative AI brings novel and impressive abilities to help people in everyday tasks. There are many AI workflows that solve real and complex problems by chaining AI outputs together with human interaction. Although there is an undeniable…

人机交互 · 计算机科学 2024-06-03 Tao Long , Katy Ilonka Gero , Lydia B. Chilton

Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Abhay Rawat , Shubham Dokania , Astitva Srivastava , Shuaib Ahmed , Haiwen Feng , Rahul Tallamraju

Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a…

人工智能 · 计算机科学 2026-04-24 Bartosz Balis , Michal Orzechowski , Piotr Kica , Michal Dygas , Michal Kuszewski

Generative Agentic AI systems are emerging as a powerful paradigm for automating complex, multi-step tasks. However, many existing frameworks for building these systems introduce significant complexity, a steep learning curve, and…

人工智能 · 计算机科学 2025-11-13 Deven Panchal

Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and workflow…

机器学习 · 计算机科学 2026-04-23 Ruocan Wei , Shufeng Wang , Ziwei Shi

Verified controller synthesis uses world models that comprise all potential behaviours of humans, robots, further equipment, and the controller to be synthesised. A world model enables quantitative risk assessment, for example, by…

软件工程 · 计算机科学 2021-10-26 Mario Gleirscher , Jan Peleska

The discovery of functional molecules is an expensive and time-consuming process, exemplified by the rising costs of small molecule therapeutic discovery. One class of techniques of growing interest for early-stage drug discovery is de novo…

定量方法 · 定量生物学 2020-02-18 Wenhao Gao , Connor W. Coley

Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined…

软件工程 · 计算机科学 2026-03-09 Bowei Xia , Mengkang Hu , Shijian Wang , Jiarui Jin , Wenxiang Jiao , Yuan Lu , Kexin Li , Ping Luo