While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk of executing out-of-distribution (OOD) actions. Recent approaches mitigate this by learning a behavior-cloning policy through flow matching and then performin...
Songyuan Zhang, Oswin So, Eric Yang Yu et al.· 0 citations
Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two consequences during optimization: (i) the objective evaluation dominates execution time, and (ii) sample-efficient algorithms are crucial to accelerate developm...
Gustavo Sutter, Alejandro Comas-Leon, David Holzm\"uller et al.· 0 citations
Spatio-temporal forecasting is a cornerstone of logistics, urban planning, and intelligent transportation systems. However, constrained by deployment costs and maintenance resources, sensor networks often lack comprehensive spatial coverage, rendering Forecast Unobserved Node States (FUNS) a critical yet formidable cha...
Shuhao Li, Weidong Yang, Changan Liu et al.· 0 citations
Inverse optimization estimates the weights of an objective function that explain observed decisions as optimal solutions, and is used in a variety of fields. For mixed-integer linear programs (MILPs), existing methods aim to reproduce the observations as optimal solutions, and thus learn compromise weights when the obs...
Akira Kitaoka· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Obsessive-compulsive disorder (OCD) is highly polygenic, and the largest genome-wide association study (GWAS) to date — 53,660 cases and 2,044,417 controls — identified only 30 loci, a small fraction of those expected to cause disease and too few to resolve the underlying biological pathways. Some dogs naturally develo...
Katarina Tengvall, Vista Sohrab, Matthew J. Christmas et al.· SciLifeLab Data Repository· 0 citations
This deposit contains the re-executable analysis pipeline and aggregate results for a two-cohort study of weekly reflective journals in an introductory linear algebra course. It accompanies a manuscript submitted to the International Journal of Mathematical Education in Science and Technology. The underlying corpus of...
Carlos Eduardo Rojas Bruna· Zenodo (CERN European Organi...· 0 citations
This folder consists of dataset and script used in the analysis presented in "A low-metallicity dwarf galaxy rapidly forming massive stars at the break of cosmic dawn", by Morishita et al., submitted to Science.
Takahiro Morishita· Zenodo (CERN European Organi...· 0 citations
Rural depopulation and territorial imbalances are ongoing challenges that require innovative tools for understanding community needs and informing evidence-based policy. Sentiment Analysis (SA) has emerged as a promising methodology for extracting emotional information from large volumes of digital text data. However,...
Emilio Hernández-López, Laura Martínez-Carrasco, Margarita Brugarolas· Humanities and Social Scienc...· 0 citations
This study aims to examine the effect of implementing the Discovery Learning model on fifth-grade students' Science Process Skills (SPS) concerning Earth's structure at SDN Gelam 1 Candi. The underlying issue was students' suboptimal science process skills stemming from conventional teacher-centered instructional pract...
This study was motivated by the low learning outcomes in Natural and Social Sciences (IPAS) among fourth-grade students at SD Negeri 173307 Sipultak, which were presumed to be influenced by teacher-centered instruction and the limited use of varied learning models and interactive instructional media. This study aimed t...
Sri Ikawati Hutauruk, Regina Sipayung, Irmina Pinem et al.· SCIENCE Jurnal Inovasi Pendi...· 0 citations
This research is motivated by the gap between the demands of the Independent Curriculum which emphasizes innovative learning and the availability of PBL-STEM-based teaching tools at SDN 021 Sungai Kunjang. Learning conditions that are still dominated by conventional methods (teacher-centered) have an impact on the lack...
Bintang Simanullang, Erna Suhartini, Muhammad Nur Mannan et al.· SCIENCE Jurnal Inovasi Pendi...· 0 citations
OBJECTIVE Cerebral proliferative angiopathy (CPA) is a rare, low-flow, diffuse vascular malformation distinct from a classic cerebral nidal arteriovenous malformation. Its clinical course, imaging features, and optimal management in pediatric patients remain unclear, and existing evidence is limited to small case serie...
Vítor Nagai Yamaki, Anoushka Alwis, Samyami Sangeeta Chowdhury et al.· Journal of Neurosurgery Pedi...· 0 citations
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
