Zobrazeno 1 - 10
of 8 603
pro vyhledávání: '"Goldblum"'
Autor:
Giuffrida A, Saia-Owenby C, Andriano C, Beall D, Bailey-Classen A, Buchanan P, Budwany R, Desai MJ, Comer A, Dudas A, Tieppo Francio V, Grace W, Gill B, Grunch B, Goldblum A, Garcia RA, Lee DW, Lavender C, Lawandy M, Mandell L, Mata R, Rabii M, Patel K, Patel RG, Patel AA, Sayed D, Singh G, Strand N, Tate J, Schatman ME, Deer T
Publikováno v:
Journal of Pain Research, Vol Volume 17, Pp 3587-3599 (2024)
Anthony Giuffrida,1 Christy Saia-Owenby,2 Chris Andriano,3,* Douglas Beall,4,* Ashley Bailey-Classen,5,* Patrick Buchanan,6,* Ryan Budwany,7,* Mehul J Desai,8,* Ashley Comer,9,* Andrew Dudas,10,* Vinicius Tieppo Franci
Externí odkaz:
https://doaj.org/article/9103d8ab1c164db981899ec5aaca51c0
As fine-tuning large language models (LLMs) becomes increasingly prevalent, users often rely on third-party services with limited visibility into their fine-tuning processes. This lack of transparency raises the question: how do consumers verify that
Externí odkaz:
http://arxiv.org/abs/2411.06611
Autor:
Stein, Alex, Sharpe, Samuel, Bergman, Doron, Kumar, Senthil, Bruss, C. Bayan, Dickerson, John, Goldstein, Tom, Goldblum, Micah
Many real-world applications of tabular data involve using historic events to predict properties of new ones, for example whether a credit card transaction is fraudulent or what rating a customer will assign a product on a retail platform. Existing a
Externí odkaz:
http://arxiv.org/abs/2410.10648
Autor:
Potapczynski, Andres, Qiu, Shikai, Finzi, Marc, Ferri, Christopher, Chen, Zixi, Goldblum, Micah, Bruss, Bayan, De Sa, Christopher, Wilson, Andrew Gordon
Dense linear layers are the dominant computational bottleneck in large neural networks, presenting a critical need for more efficient alternatives. Previous efforts focused on a small number of hand-crafted structured matrices and neglected to invest
Externí odkaz:
http://arxiv.org/abs/2410.02117
Autor:
Feuer, Benjamin, Goldblum, Micah, Datta, Teresa, Nambiar, Sanjana, Besaleli, Raz, Dooley, Samuel, Cembalest, Max, Dickerson, John P.
The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior alignment by virtue of better correspondence with human pairwise pref
Externí odkaz:
http://arxiv.org/abs/2409.15268
Autor:
Goldblum, Zack, Xu, Zhongchuan, Shi, Haoer, Orzechowski, Patryk, Spence, Jamaal, Davis, Kathryn A, Litt, Brian, Sinha, Nishant, Wagenaar, Joost
The exponential growth of neuroscientific data necessitates platforms that facilitate data management and multidisciplinary collaboration. In this paper, we introduce Pennsieve - an open-source, cloud-based scientific data management platform built t
Externí odkaz:
http://arxiv.org/abs/2409.10509
Autor:
Lotfi, Sanae, Kuang, Yilun, Amos, Brandon, Goldblum, Micah, Finzi, Marc, Wilson, Andrew Gordon
Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous for large models at the billion
Externí odkaz:
http://arxiv.org/abs/2407.18158
Autor:
White, Colin, Dooley, Samuel, Roberts, Manley, Pal, Arka, Feuer, Ben, Jain, Siddhartha, Shwartz-Ziv, Ravid, Jain, Neel, Saifullah, Khalid, Naidu, Siddartha, Hegde, Chinmay, LeCun, Yann, Goldstein, Tom, Neiswanger, Willie, Goldblum, Micah
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render benchmarks obsolete. To mitigate this, many recent benchmarks crowdsource
Externí odkaz:
http://arxiv.org/abs/2406.19314
Publikováno v:
Nucl. Instrum. Meth. A 1069 (2024), 169859
The Cs$_2$LiYCl$_6$:Ce (CLYC) elpasolite scintillator is known for its response to fast and thermal neutrons along with good $\gamma$-ray energy resolution. While the $^{35}$Cl($n,p$) reaction has been identified as a potential means for CLYC-based f
Externí odkaz:
http://arxiv.org/abs/2406.15730
Autor:
Shwartz-Ziv, Ravid, Goldblum, Micah, Bansal, Arpit, Bruss, C. Bayan, LeCun, Yann, Wilson, Andrew Gordon
It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters, underpinning notions of overparameterized and underparameterized models. In practice, however, we only find solutions accessi
Externí odkaz:
http://arxiv.org/abs/2406.11463