Zobrazeno 1 - 10
of 2 370
pro vyhledávání: '"Giles, C."'
Resolving the dichotomy between the human-like yet constrained reasoning processes of Cognitive Architectures and the broad but often noisy inference behavior of Large Language Models (LLMs) remains a challenging but exciting pursuit, for enabling re
Externí odkaz:
http://arxiv.org/abs/2408.09176
Pseudocode in a scholarly paper provides a concise way to express the algorithms implemented therein. Pseudocode can also be thought of as an intermediary representation that helps bridge the gap between programming languages and natural languages. H
Externí odkaz:
http://arxiv.org/abs/2406.04635
Prompting techniques have significantly enhanced the capabilities of Large Language Models (LLMs) across various complex tasks, including reasoning, planning, and solving math word problems. However, most research has predominantly focused on languag
Externí odkaz:
http://arxiv.org/abs/2405.13209
Autor:
Hsu, Ting-Yao, Huang, Chieh-Yang, Huang, Shih-Hong, Rossi, Ryan, Kim, Sungchul, Yu, Tong, Giles, C. Lee, Huang, Ting-Hao K.
Crafting effective captions for figures is important. Readers heavily depend on these captions to grasp the figure's message. However, despite a well-developed set of AI technologies for figures and captions, these have rarely been tested for usefuln
Externí odkaz:
http://arxiv.org/abs/2403.17784
Autor:
Srinath, Mukund, Venkit, Pranav, Badillo, Maria, Schaub, Florian, Giles, C. Lee, Wilson, Shomir
Privacy policies are crucial for informing users about data practices, yet their length and complexity often deter users from reading them. In this paper, we propose an automated approach to identify and visualize data practices within privacy polici
Externí odkaz:
http://arxiv.org/abs/2402.11006
This paper analyzes two competing rule extraction methodologies: quantization and equivalence query. We trained $3600$ RNN models, extracting $18000$ DFA with a quantization approach (k-means and SOM) and $3600$ DFA by equivalence query($L^{*}$) meth
Externí odkaz:
http://arxiv.org/abs/2402.02627
Autor:
Hsu, Ting-Yao, Huang, Chieh-Yang, Rossi, Ryan, Kim, Sungchul, Giles, C. Lee, Huang, Ting-Hao K.
There is growing interest in systems that generate captions for scientific figures. However, assessing these systems output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends
Externí odkaz:
http://arxiv.org/abs/2310.15405
Autor:
Aehle, Max, Arsini, Lorenzo, Barreiro, R. Belén, Belias, Anastasios, Bury, Florian, Cebrian, Susana, Demin, Alexander, Dickinson, Jennet, Donini, Julien, Dorigo, Tommaso, Doro, Michele, Gauger, Nicolas R., Giammanco, Andrea, Gray, Lindsey, González, Borja S., Kain, Verena, Kieseler, Jan, Kusch, Lisa, Liwicki, Marcus, Maier, Gernot, Nardi, Federico, Ratnikov, Fedor, Roussel, Ryan, de Austri, Roberto Ruiz, Sandin, Fredrik, Schenk, Michael, Scarpa, Bruno, Silva, Pedro, Strong, Giles C., Vischia, Pietro
In this article we examine recent developments in the research area concerning the creation of end-to-end models for the complete optimization of measuring instruments. The models we consider rely on differentiable programming methods and on the spec
Externí odkaz:
http://arxiv.org/abs/2310.05673
Autor:
Strong, Giles C., Lagrange, Maxime, Orio, Aitor, Bordignon, Anna, Bury, Florian, Dorigo, Tommaso, Giammanco, Andrea, Heikal, Mariam, Kieseler, Jan, Lamparth, Max, del Árbol, Pablo Martínez Ruíz, Nardi, Federico, Vischia, Pietro, Zaraket, Haitham
We describe a software package, TomOpt, developed to optimise the geometrical layout and specifications of detectors designed for tomography by scattering of cosmic-ray muons. The software exploits differentiable programming for the modeling of muon
Externí odkaz:
http://arxiv.org/abs/2309.14027
Autor:
Chakravorti, Tatiana, Fraleigh, Robert, Fritton, Timothy, McLaughlin, Michael, Singh, Vaibhav, Griffin, Christopher, Kwasnica, Anthony, Pennock, David, Giles, C. Lee, Rajtmajer, Sarah
We present a prototype hybrid prediction market and demonstrate the avenue it represents for meaningful human-AI collaboration. We build on prior work proposing artificial prediction markets as a novel machine-learning algorithm. In an artificial pre
Externí odkaz:
http://arxiv.org/abs/2303.00866