Tootfinder

Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation
Benjamin Elder, Anupama Murthi, Jungkoo Kang, Ankita Rajaram Naik, Kiran Kate, Kinjal Basu, Danish Contractor
https://arxiv.org/abs/2506.11266

Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation
Large language models (LLMs) are routinely deployed as agentic systems, with access to tools that interact with live environments to accomplish tasks. In enterprise deployments these systems need to interact with API collections that can be extremely large and complex, often backed by databases. In order to create datasets with such characteristics, we explore how existing NL2SQL (Natural Language to SQL query) datasets can be used to automatically create NL2API datasets. Specifically, this wor…

Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition
Tao Zhong, Mengzhe Geng, Shujie Hu, Guinan Li, Xunying Liu
https://arxiv.org/abs/2506.11069

Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition
Accurate recognition of dysarthric and elderly speech remains challenging to date. While privacy concerns have driven a shift from centralized approaches to federated learning (FL) to ensure data confidentiality, this further exacerbates the challenges of data scarcity, imbalanced data distribution and speaker heterogeneity. To this end, this paper conducts a systematic investigation of regularized FL techniques for privacy-preserving dysarthric and elderly speech recognition, addressing differ…

Rare Events, Many Searchers, and Fast Target Reaching in a Finite Domain
Elisabetta Ellettari, Giacomo Nasuti, Alberto Bassanoni, Alessandro Vezzani, Raffaella Burioni
https://arxiv.org/abs/2507.09452

Rare Events, Many Searchers, and Fast Target Reaching in a Finite Domain
Finding a target in a complex environment is a fundamental challenge in nature, from chemical reactions to sperm reaching an egg. An effective strategy to reduce the time needed to reach a target is to deploy many searchers, increasing the likelihood that at least one will succeed by using the statistics of rare events. When the underlying stochastic process involves broadly distributed step sizes, rare long jumps dominate the dynamics, making the use of multiple searchers particularly powerful…

Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flows
Zhecheng Liu, Jeff D. Eldredge
https://arxiv.org/abs/2506.10153

Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flows
A linear flow control strategy designed for weak disturbances may not remain effective in sequences of strong disturbances due to nonlinear interactions, but it is sensible to leverage it for developing a better strategy. In the present study, we propose a transformer-based reinforcement learning (RL) framework to learn an effective control strategy for regulating aerodynamic lift in gust sequences via pitch control. The transformer addresses the challenge of partial observability from limited …

Statistics on $\ell$-interval parking functions
Kyle Celano, Jennifer Elder, Kimberly P. Hadaway, Pamela E. Harris, Jeremy L. Martin, Amanda Priestley, Gabe Udell
https://arxiv.org/abs/2507.07243

Statistics on $\ell$-interval parking functions
The displacement of a car with respect to a parking function is the number of spots it must drive past its preferred spot in order to park. An $\ell$-interval parking function is one in which each car has displacement at most $\ell$. Among our results, we enumerate $\ell$-interval parking functions with respect to statistics such as inversion, displacement, and major index. We show that $1$-interval parking functions with fixed displacement exhibit a cyclic sieving phenomenon. We give closed fo…

Exploring the Convergence of HCI and Evolving Technologies in Information Systems
Rajan Das Gupta, Ashikur Rahman, Md Imrul Hasan Showmick, Md. Yeasin Rahat, Md. Jakir Hossen
https://arxiv.org/abs/2506.08549

Exploring the Convergence of HCI and Evolving Technologies in Information Systems
Modern technology driven information systems are part of our daily lives. However, this deep integration poses new challenges to the human computer interaction (HCI) professionals. With the rapid growth of mobile and cloud computing and the Internet of Things (IoT), the demand for HCI specialists to design user-friendly and adaptable interfaces has never been more pressing. Especially for diverse user groups such as children, the elderly and people with disabilities who need interfaces tailored…

Predicting Postoperative Stroke in Elderly SICU Patients: An Interpretable Machine Learning Model Using MIMIC Data
Tinghuan Li, Shuheng Chen, Junyi Fan, Elham Pishgar, Kamiar Alaei, Greg Placencia, Maryam Pishgar
https://arxiv.org/abs/2506.03209

Predicting Postoperative Stroke in Elderly SICU Patients: An Interpretable Machine Learning Model Using MIMIC Data
Postoperative stroke remains a critical complication in elderly surgical intensive care unit (SICU) patients, contributing to prolonged hospitalization, elevated healthcare costs, and increased mortality. Accurate early risk stratification is essential to enable timely intervention and improve clinical outcomes. We constructed a combined cohort of 19,085 elderly SICU admissions from the MIMIC-III and MIMIC-IV databases and developed an interpretable machine learning (ML) framework to predict in…

Intergalactic Medium Tomography with the Sunburst Arc
Michelle A. Berg, John Chisholm, J. Xavier Prochaska, T. Emil Rivera-Thorsen, Michael D. Gladders, Keren Sharon, Claus Leitherer, J. J. Eldridge, Matthew Bayliss, Haakon Dahle, Jane R. Rigby, Anne Verhamme
https://arxiv.org/abs/2507.06443…

Intergalactic Medium Tomography with the Sunburst Arc
Gravitational lensing has transformed the field of gas tomography in the intergalactic medium (IGM) and circumgalactic medium (CGM). Here we use the brightest lensed galaxy identified to date, the Sunburst Arc ($z$$\approx$2.37), to constrain the physical size of foreground absorbers at $z$$\approx$2 in 2D. This galaxy is a confirmed Lyman continuum leaker, where its single leaking region is imaged 12 times over four separate arcs. The separations between the arcs allows for large scale tomogra…

Immersive Technologies and Elderly Users: Current use, Limitations and Future Perspectives
Zoe Anastasiadou, Andreas Lanitis
https://arxiv.org/abs/2506.22932

Immersive Technologies and Elderly Users: Current use, Limitations and Future Perspectives
The increase of the percentage of elderly population in modern societies dictates the use of emerging technologies as a means of supporting elder members of the society. Within this scope, Extended Reality (XR) technologies pose as a promising technology for improving the daily lives of the elderly population. This paper presents a literature review that describes the most common characteristics of the physical and mental state of the elderly, allowing readers, and specifically XR developers, t…

Crafting Hanzi as Narrative Bridges: An AI Co-Creation Workshop for Elderly Migrants
Wen Zhan, Ziqun Hua, Peiyue Lin, Yunfei Chen
https://arxiv.org/abs/2507.01548

Crafting Hanzi as Narrative Bridges: An AI Co-Creation Workshop for Elderly Migrants
This paper explores how older adults, particularly aging migrants in urban China, can engage AI-assisted co-creation to express personal narratives that are often fragmented, underrepresented, or difficult to verbalize. Through a pilot workshop combining oral storytelling and the symbolic reconstruction of Hanzi, participants shared memories of migration and recreated new character forms using Xiaozhuan glyphs, suggested by the Large Language Model (LLM), together with physical materials. Suppo…