Institutional efforts to advance racial equity within professional associations, credentialing bodies, and accrediting organizations are commonly built on two fragile models: compliance-driven mandates (which collapse when enforcement is paused or politically targeted) and isolated, time-limited initiatives (which lack...
Isha W. Metzger, Kimberly Boller· Societies· 0 citations
While Part-of-speech tagging is considered a well-understood task in the literature, most work has focused on indo-european languages with fusional morphology. For low-resource agglutinative languages, such as brazillian indigenous languages, the task is commonly constrained by small annotated corpora, high lexical spa...
Jonas Oliveira Pereira, Lílian Teixeira de Sousa, Marlo Souza· Brazilian Symposium in Infor...· 0 citations
Surgical mitral valve repair is the preferred treatment for degenerative mitral regurgitation (MR) and is also widely performed for MR of other etiologies; however, recurrent MR after repair is not uncommon and is associated with adverse left ventricular remodeling and increased risks of mitral valve reintervention and...
JM Kong, Mingyang Yu, Jingxin Zhou· Open Science Framework· 0 citations
Membrane transporters mediate cellular chemical exchange, yet their substrate specificities remain poorly characterized, with experimental studies constrained by the instability of membrane proteins. Existing computational tools often target narrow substrate classes or fail to generalize to distant homologs. We present...
Tong Pan, Jie Liu, Jing Xu et al.· Genome biology· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Code, prompts, results, and cached model responses for the article "A Capability Threshold for Large Language Model Agents in Anti-Money Laundering: A Controlled Evaluation of Twenty-One Models" (Y. R. Parikh and E. K. Saraiya, submitted to IEEE Access). An investigation starts from one alerted laundering transaction a...
Most systems that answer questions from an organization's documents cut each document into small chunks, fetch the few chunks that look most like the question, and ask a language model to write an answer from them. This works when the answer sits in one place. It works poorly when the answer is spread over several docu...
Driver action recognition (DAR) is a core capability of advanced driver assistance systems, however, it remains difficult because distracted driver actions involve small interacting objects, subtle hand movements, and severe self-occlusion inside a confined cabin. Most existing methods are trained on pre-segmented vide...
Hiep Bui Hoang, Binh Nguyen Thuy, Lĩnh Võ Thiện et al.· Data Science and Artificial...· 0 citations
Semantic Language Models for WCAG — data, code and supplementary analyses Supplementary material for: B. O. Kuzikov, O. A. Shovkoplias, P. O. Tytov, S. R. Shovkoplias, O. V. Shutylieva, O. V. Vlasenko. A Statistical Framework for Consensus-Based Reliability Assessment in Large Language Model Evaluation Applied to Web A...
Borys Kuzikov, O. A. Shovkoplyas, П. О. Титов et al.· Zenodo (CERN European Organi...· 0 citations
The use of textbooks as primary sources of information has increasingly given way to tools based on Large Language Models (LLMs), raising concerns about the reliability of generated answers. This study investigates how different adaptation strategies shape the behavior of small language models in educational Question A...
Lucas B. Bulcão Mota, Larrissa Dantas, D. Claro et al.· Brazilian Symposium in Infor...· 0 citations
Alternatives to Large Language Models have been proposed to develop smaller models that require substantially less training data. In this paper, we propose a monolingual (Portuguese) Hybrid Transformer model trained with only 260M words, whose size is comparable to that of small Encoder-based models. After pre-training...
Miguel M. Carpi, I. Silveira, D. D. Mauá et al.· Brazilian Symposium in Infor...· 0 citations
Autonomous discovery loops, in which language-model agents improve a design against an automatic evaluator, spend most of their effort on ideas that fail. We argue that such a loop should be built so that a failure is cheap and a success is not capped, and that the part that decides what to try should be scored like ev...
Krish Ghosh· Zenodo (CERN European Organi...· 0 citations
Over the past four decades, neoliberal reforms have reshaped education systems globally. Among these, school consolidation remains a popular policy instrument promising efficiency, consistency, and scale. In some urban contexts, however, consolidation has produced uneven impacts along racial and socioeconomic lines. Th...
Oscar Wycisk, Francis Markham, Marnie O’Bryan· Annals of the American Assoc...· 0 citations
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
