Zobrazeno 1 - 10
of 180 973
pro vyhledávání: '"SRINIVASAN, A"'
Autor:
He, Yuntian, Maneriker, Pranav, Srinivasan, Anutam, Vadlamani, Aditya T., Parthasarathy, Srinivasan
Conformal Prediction is a robust framework that ensures reliable coverage across machine learning tasks. Although recent studies have applied conformal prediction to graph neural networks, they have largely emphasized post-hoc prediction set generati
Externí odkaz:
http://arxiv.org/abs/2410.21618
Autor:
Pagnoni, Artidoro, Pasunuru, Ram, Rodriguez, Pedro, Nguyen, John, Muller, Benjamin, Li, Margaret, Zhou, Chunting, Yu, Lili, Weston, Jason, Zettlemoyer, Luke, Ghosh, Gargi, Lewis, Mike, Holtzman, Ari, Iyer, Srinivasan
We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT encodes bytes in
Externí odkaz:
http://arxiv.org/abs/2412.09871
Autor:
Joglekar, Advait, Umesh, Srinivasan
Neural Machine Translation (NMT) models are typically trained on datasets with limited exposure to Scientific, Technical and Educational domains. Translation models thus, in general, struggle with tasks that involve scientific understanding or techni
Externí odkaz:
http://arxiv.org/abs/2412.09025
Autor:
Trevithick, Alex, Paiss, Roni, Henzler, Philipp, Verbin, Dor, Wu, Rundi, Alzayer, Hadi, Gao, Ruiqi, Poole, Ben, Barron, Jonathan T., Holynski, Aleksander, Ramamoorthi, Ravi, Srinivasan, Pratul P.
Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to
Externí odkaz:
http://arxiv.org/abs/2412.07696
Autor:
Zhang, Ruiqi, Motes, Brandon, Tan, Shaun, Lu, Yongli, Shih, Meng-Chen, Hao, Yilun, Yang, Karen, Srinivasan, Shreyas, Bawendi, Moungi G., Bulovic, Vladimir
We demonstrate a machine learning (ML) approach that accurately predicts the current-voltage behavior of 3D/2D-structured (FAMA)Pb(IBr)3/OABr hybrid organic-inorganic halide perovskite (HOIP) solar cells under AM1.5 illumination. Our neural network a
Externí odkaz:
http://arxiv.org/abs/2412.09638
We propose a novel method for measuring the discrepancy between a set of samples and a desired posterior distribution for Bayesian inference. Classical methods for assessing sample quality like the effective sample size are not appropriate for scalab
Externí odkaz:
http://arxiv.org/abs/2412.05135
Autor:
von der Heyde, Benjamin, Srinivasan, Anand, Birwa, Sumit Kumar, von der Heyde, Eva Laura, Höhn, Steph S. M. H., Goldstein, Raymond E., Hallmann, Armin
The evolution of multicellularity involved the transformation of a simple cell wall of unicellular ancestors into a complex, multifunctional extracellular matrix (ECM). A suitable model organism to study the formation and expansion of an ECM during o
Externí odkaz:
http://arxiv.org/abs/2412.05059
Autor:
Zhu, Xiao, Iyengar, Srinivasan S.
Computing high dimensional potential surfaces for molecular and materials systems is considered to be a great challenge in computational chemistry with potential impact in a range of areas including fundamental prediction of reaction rates. In this p
Externí odkaz:
http://arxiv.org/abs/2412.03831
The accurate computational study of wavepacket nuclear dynamics is considered to be a classically intractable problem, particularly with increasing dimensions. Here we present two algorithms that, in conjunction with other methods developed by us, wi
Externí odkaz:
http://arxiv.org/abs/2412.03763
Autor:
Omi, Asif Iftekhar, Farina, Emma, Jiang, Anyu, Khalifa, Adam, Srinivasan, Shriya, Chatterjee, Baibhab
Body-coupled powering (BCP) is an innovative wireless power transfer (WPT) technique, recently explored for its potential to deliver power to cutting-edge biomedical implants such as nerve and muscle stimulators. This paper demonstrates the efficient
Externí odkaz:
http://arxiv.org/abs/2412.03488