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