Zobrazeno 1 - 10
of 451
pro vyhledávání: '"Gomes, Carla P"'
AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification
Autor:
Hogan, Brendan, Kabra, Anmol, Pacheco, Felipe Siqueira, Greenstreet, Laura, Fan, Joshua, Ferber, Aaron, Ummus, Marta, Brito, Alecsander, Graham, Olivia, Aoki, Lillian, Harvell, Drew, Flecker, Alex, Gomes, Carla
Trust and interpretability are crucial for the use of Artificial Intelligence (AI) in scientific research, but current models often operate as black boxes offering limited transparency and justifications for their outputs. We introduce AiSciVision, a
Externí odkaz:
http://arxiv.org/abs/2410.21480
Autor:
Du, Yuanqi, Plainer, Michael, Brekelmans, Rob, Duan, Chenru, Noé, Frank, Gomes, Carla P., Aspuru-Guzik, Alán, Neklyudov, Kirill
Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large space of trajectories. For settings where the dynamical system of intere
Externí odkaz:
http://arxiv.org/abs/2410.07974
The ability to form, retrieve, and reason about memories in response to stimuli serves as the cornerstone for general intelligence - shaping entities capable of learning, adaptation, and intuitive insight. Large Language Models (LLMs) have proven the
Externí odkaz:
http://arxiv.org/abs/2409.15566
Modern neural network classifiers achieve remarkable performance across a variety of tasks; however, they frequently exhibit overconfidence in their predictions due to the cross-entropy loss. Inspired by this problem, we propose the \textbf{Cr}i\text
Externí odkaz:
http://arxiv.org/abs/2409.15565
Autor:
Zhou, Jin Peng, Belardi, Christian K., Wu, Ruihan, Zhang, Travis, Gomes, Carla P., Sun, Wen, Weinberger, Kilian Q.
Developing prompt-based methods with Large Language Models (LLMs) requires making numerous decisions, which give rise to a combinatorial search problem. For example, selecting the right pre-trained LLM, prompt, and hyperparameters to attain the best
Externí odkaz:
http://arxiv.org/abs/2407.06172
Autor:
Duan, Chenru, Liu, Guan-Horng, Du, Yuanqi, Chen, Tianrong, Zhao, Qiyuan, Jia, Haojun, Gomes, Carla P., Theodorou, Evangelos A., Kulik, Heather J.
Transition states (TSs) are transient structures that are key in understanding reaction mechanisms and designing catalysts but challenging to be captured in experiments. Alternatively, many optimization algorithms have been developed to search for TS
Externí odkaz:
http://arxiv.org/abs/2404.13430
Autor:
Min, Yimeng, Gomes, Carla P.
We study the generalization capability of Unsupervised Learning in solving the Travelling Salesman Problem (TSP). We use a Graph Neural Network (GNN) trained with a surrogate loss function to generate an embedding for each node. We use these embeddin
Externí odkaz:
http://arxiv.org/abs/2403.20212
Autor:
Kong, Lingkai, Du, Yuanqi, Mu, Wenhao, Neklyudov, Kirill, De Bortoli, Valentin, Wu, Dongxia, Wang, Haorui, Ferber, Aaron, Ma, Yi-An, Gomes, Carla P., Zhang, Chao
Addressing real-world optimization problems becomes particularly challenging when analytic objective functions or constraints are unavailable. While numerous studies have addressed the issue of unknown objectives, limited research has focused on scen
Externí odkaz:
http://arxiv.org/abs/2402.18012
Autor:
Chang, Ming-Chiang, Ament, Sebastian, Amsler, Maximilian, Sutherland, Duncan R., Zhou, Lan, Gregoire, John M., Gomes, Carla P., van Dover, R. Bruce, Thompson, Michael O.
X-ray diffraction (XRD) is an essential technique to determine a material's crystal structure in high-throughput experimentation, and has recently been incorporated in artificially intelligent agents in autonomous scientific discovery processes. Howe
Externí odkaz:
http://arxiv.org/abs/2308.07897
Autor:
Zenil, Hector, Tegnér, Jesper, Abrahão, Felipe S., Lavin, Alexander, Kumar, Vipin, Frey, Jeremy G., Weller, Adrian, Soldatova, Larisa, Bundy, Alan R., Jennings, Nicholas R., Takahashi, Koichi, Hunter, Lawrence, Dzeroski, Saso, Briggs, Andrew, Gregory, Frederick D., Gomes, Carla P., Rowe, Jon, Evans, James, Kitano, Hiroaki, King, Ross
Recent advances in machine learning and AI, including Generative AI and LLMs, are disrupting technological innovation, product development, and society as a whole. AI's contribution to technology can come from multiple approaches that require access
Externí odkaz:
http://arxiv.org/abs/2307.07522