21 papers · ranked by Valyu relevance
Nicholas Sadjoli, Tim Siefken, Atin Ghosh, Yifan Mai + 1 more
Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from the common industry practice of using prompt optimization (PO) techniques to optimize the prompt for each model to maximize application performance. In this paper, we…
Wenjing Tang, Xuanjin Jin, Yuan Liu, Renming Huang + 2 more
Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov Decision Process (POMDP) models for real robotics domains remains difficult and labor-intensive. We introduce PO-PDDL, a symbolic formulation of POMDPs that…
Marijan Ribarič, Luka Šušteršič
Abstract. Abstract.We introduce four original concepts. First, the point-like object (PO) specified as a classical extended real object whose response to an external force is aptly specified solely by the trajectory of a single point, whose velocity eventually stops changing after the cessation of the external force.…
Chris J. Selman, Katherine J. Lee, Steven Y. C. Tong, Mark Jones + 1 more
Background: The proportional odds (PO) model is the most common analytic method for ordinal outcomes in randomised controlled trials. While parameter estimates obtained under departures from PO can be interpreted as an average odds ratio, they can obscure differing treatment effects across the distribution of the…
Göksel Mısırlı, Bill Yang, Katherine James, Anil Wipat
Engineering genetic regulatory circuits is key to the creation of biological applications that are responsive to environmental changes. Computational models can assist in understanding especially large and complex circuits where manual analysis is infeasible, permitting a model-driven design process. However, there are…
Andrew Kwok Fai Lui, Yin Hei Chan, Kevin Hung, Kah Phooi Seng
Functional objects are large and small physical entities installed in urban environments to offer specific functionalities to visitors, such as shops, escalators, and information kiosks. Instances of the novel notion are focal points of human activities and are significant in pedestrian movement. Pedestrian trajectory…
Authors not listed
In our effort to more reliably leverage large language models for designing effective photoresponsive molecular materials for drug delivery, we developed the Explanation CPO (XCPO), an end-to-end reinforcement learning fine-tuning workflow. The maturity of RLHF techniques has greatly stimulated the flourishing…
Ding Li, Tiantian Fang, Shaojiang Li
Objective This study aimed to develop a predictive model for postoperative urinary tract infection (PO-UTI) in ureteral stone patients, addressing limitations of traditional research methods and advancing perioperative infection management from experience-driven to data-driven transformation. Methods A retrospective…
Mohamed S. Abdelwahab, Mohamed E. Mahmoud, Rasha A. Metwally
This study developed a novel, eco-friendly solid-phase extraction (SPE) sorbent, modified pomegranate biochar (POM), from the agricultural waste of pomegranate peel for the efficient removal of toxic lead (Pb(II)) and the tetracycline (TC) antibiotic from aqueous solutions. Synthesized POM was comprehensively…
Shuya Nakata, Yoshiharu Mori, Shigenori Tanaka
Ultra-large virtual chemical spaces have emerged as a valuable resource for drug discovery, providing access to billions of make-on-demand compounds with high synthetic success rates. Chemical language models can potentially accelerate the exploration of these vast spaces through direct compound generation. However…
DuYeong Heo, Jae Yeal Nam, Byoung Chul Ko
Semi-supervised learning is known to achieve better generalisation than a model learned solely from labelled data. Therefore, we propose a new method for estimating a pedestrian pose orientation using a soft-target method, which is a type of semi-supervised learning method. Because a convolutional neural network (CNN)…
Authors not listed
Kinetic modeling is essential for predicting changes in food quality during processing and storage. This study evaluates the application of physics-informed neural networks (PINN) for food kinetic modeling, integrating kinetic insights into neural network frameworks. Based on three case studies, namely seed drying…
Mathias Foo, Leander Dony, Fei He
Recent advances in synthetic biology have enabled the design of genetic feedback control circuits that could be implemented to build resilient plants against pathogen attacks. To facilitate the proper design of these genetic feedback control circuits, an accurate model that is able to capture the vital dynamical…
Chen M. Chen, Rosemary Yu
Plasticity is the potential for cells or cell populations to change their phenotypes and behaviours in response to internal or external cues. A common way to study a plasticity programme is to track the underlying molecular changes over time, by collecting omics time-series data. However, there remains a lack of…
Jessica S. Yu, Blair Lyons, Susanne Rafelski, Julie A. Theriot + 2 more
Iterating between data-driven research and generative computational models is a powerful approach for emulating biological systems, testing hypotheses, and gaining a deeper understanding of these systems. We developed a hybrid agent-based model (ABM) that integrates a Cellular Potts Model (CPM) designed to investigate…
Lilija Wehling, Gurdeep Singh, Ahmad Wisnu Mulyadi, Rakesh Hadne Sreenath + 9 more
In this study, we present Talk2Biomodels (T2B), an open-source^1^, user-friendly, large language model-based agentic AI platform designed to democratize access to computational models of biological interactions and promote the FAIRification (Findability, Accessibility, Interoperability, and Reusability) of these…
Przemysław Biecek
The data revolution has generated a huge demand for data-driven solutions. This demand propels a growing number of easy-to-use tools and training for aspiring data scientists that enable the rapid building of predictive models. Today, weapons of math destruction can be easily built and deployed without detailed…
Catherine Bjerre Collin, Tom Gebhardt, Martin Golebiewski, Tugce Karaderi + 7 more
'Tugce Karaderi' 'Maximilian Hillemanns' 'Faiz Muhammad Khan' 'Ali Salehzadeh-Yazdi' 'Marc Kirschner' 'Sylvia Krobitsch' '' 'Lars Kuepfer' 'William J. Duddy'] The future development of personalized medicine depends on a vast exchange of data from different sources, as well as harmonized integrative analysis of…
Martin Obermeier, Steven Braun, Birgit Vogel‐Heuser
—This paper presents the modular automation for reuse in manufacturing systems (modAT4rMS) approach to support the model-driven engineering (MDE) of object oriented manufacturing automation software with regard to its usability and software modularity. With usability we refer to the aspects effectiveness, efficiency…
Kacy K Verdi, Heidi JC Ellis, Michael R Gryk
Background Scientific workflows improve the process of scientific experiments by making computations explicit, underscoring data flow, and emphasizing the participation of humans in the process when intuition and human reasoning are required. Workflows for experiments also highlight transitions among experimental…
Bryan Glazer, Jonathan Lifferth, Carlos F. Lopez
Many important processes in biology, such as signaling and gene regulation, can be described using logic models. These logic models are typically built to behaviorally emulate experimentally observed phenotypes, which are assumed to be steady states of a biological system. Most models are built by hand and therefore…