Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Gruver, Nate"'
Autor:
Kapoor, Sanyam, Gruver, Nate, Roberts, Manley, Collins, Katherine, Pal, Arka, Bhatt, Umang, Weller, Adrian, Dooley, Samuel, Goldblum, Micah, Wilson, Andrew Gordon
When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is sufficient to produce calibrated uncertainties, while others introduce
Externí odkaz:
http://arxiv.org/abs/2406.08391
Autor:
Gruver, Nate, Sriram, Anuroop, Madotto, Andrea, Wilson, Andrew Gordon, Zitnick, C. Lawrence, Ulissi, Zachary
We propose fine-tuning large language models for generation of stable materials. While unorthodox, fine-tuning large language models on text-encoded atomistic data is simple to implement yet reliable, with around 90% of sampled structures obeying phy
Externí odkaz:
http://arxiv.org/abs/2402.04379
By encoding time series as a string of numerical digits, we can frame time series forecasting as next-token prediction in text. Developing this approach, we find that large language models (LLMs) such as GPT-3 and LLaMA-2 can surprisingly zero-shot e
Externí odkaz:
http://arxiv.org/abs/2310.07820
Autor:
Gruver, Nate, Stanton, Samuel, Frey, Nathan C., Rudner, Tim G. J., Hotzel, Isidro, Lafrance-Vanasse, Julien, Rajpal, Arvind, Cho, Kyunghyun, Wilson, Andrew Gordon
Publikováno v:
Advances in Neural Information Processing Systems 36, December 10-16, 2023
A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. The generative model samples plausible sequences while the discriminative model guides a search for sequences with high fitnes
Externí odkaz:
http://arxiv.org/abs/2305.20009
Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying the foreg
Externí odkaz:
http://arxiv.org/abs/2210.11369
Equivariance guarantees that a model's predictions capture key symmetries in data. When an image is translated or rotated, an equivariant model's representation of that image will translate or rotate accordingly. The success of convolutional neural n
Externí odkaz:
http://arxiv.org/abs/2210.02984
Autor:
Stanton, Samuel, Maddox, Wesley, Gruver, Nate, Maffettone, Phillip, Delaney, Emily, Greenside, Peyton, Wilson, Andrew Gordon
Bayesian optimization (BayesOpt) is a gold standard for query-efficient continuous optimization. However, its adoption for drug design has been hindered by the discrete, high-dimensional nature of the decision variables. We develop a new approach (La
Externí odkaz:
http://arxiv.org/abs/2203.12742
Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world systems, su
Externí odkaz:
http://arxiv.org/abs/2202.04836
Adaptive Informative Path Planning (AIPP) problems model an agent tasked with obtaining information subject to resource constraints in unknown, partially observable environments. Existing work on AIPP has focused on representing observations about th
Externí odkaz:
http://arxiv.org/abs/2003.09746
Autor:
Gruver, Nate, Malik, Ali, Capoor, Brahm, Piech, Chris, Stevens, Mitchell L., Paepcke, Andreas
Understanding large-scale patterns in student course enrollment is a problem of great interest to university administrators and educational researchers. Yet important decisions are often made without a good quantitative framework of the process under
Externí odkaz:
http://arxiv.org/abs/1905.13383