Zobrazeno 21 - 30
of 52 710
pro vyhledávání: '"Lyle A."'
Autor:
Stan, Gabriela Ben Melech, Aflalo, Estelle, Rohekar, Raanan Yehezkel, Bhiwandiwalla, Anahita, Tseng, Shao-Yen, Olson, Matthew Lyle, Gurwicz, Yaniv, Wu, Chenfei, Duan, Nan, Lal, Vasudev
In the rapidly evolving landscape of artificial intelligence, multi-modal large language models are emerging as a significant area of interest. These models, which combine various forms of data input, are becoming increasingly popular. However, under
Externí odkaz:
http://arxiv.org/abs/2404.03118
As is well-known, numerical experiments show that Napoleon's Theorem for planar triangles does not extend to a similar statement for triangles on the unit sphere $S^2$. Spherical triangles for which an extension of Napoleon's Theorem holds are called
Externí odkaz:
http://arxiv.org/abs/2403.02830
Autor:
Lyle, Clare, Zheng, Zeyu, Khetarpal, Khimya, van Hasselt, Hado, Pascanu, Razvan, Martens, James, Dabney, Will
Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this assumption is
Externí odkaz:
http://arxiv.org/abs/2402.18762
Autor:
Rai, Sunny, Zaveri, Khushang Jilesh, Havaldar, Shreya, Nema, Soumna, Ungar, Lyle, Guntuku, Sharath Chandra
Social emotions such as shame and pride reflect social sanctions or approvals in society. In this paper, we examine how expressions of shame and pride vary across cultures and harness them to extract unspoken normative expectations across cultures. W
Externí odkaz:
http://arxiv.org/abs/2402.11333
Autor:
Obando-Ceron, Johan, Sokar, Ghada, Willi, Timon, Lyle, Clare, Farebrother, Jesse, Foerster, Jakob, Dziugaite, Gintare Karolina, Precup, Doina, Castro, Pablo Samuel
The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, ho
Externí odkaz:
http://arxiv.org/abs/2402.08609
We propose a new algorithm for model-based distributional reinforcement learning (RL), and prove that it is minimax-optimal for approximating return distributions with a generative model (up to logarithmic factors), resolving an open question of Zhan
Externí odkaz:
http://arxiv.org/abs/2402.07598
This paper introduces a public dataset of 1.4 million procedurally-generated bicycle designs represented parametrically, as JSON files, and as rasterized images. The dataset is created through the use of a rendering engine which harnesses the BikeCAD
Externí odkaz:
http://arxiv.org/abs/2402.05301
Topology optimization is a critical task in engineering design, where the goal is to optimally distribute material in a given space for maximum performance. We introduce Neural Implicit Topology Optimization (NITO), a novel approach to accelerate top
Externí odkaz:
http://arxiv.org/abs/2402.05073
The capabilities of transformer networks such as ChatGPT and other Large Language Models (LLMs) have captured the world's attention. The crucial computational mechanism underlying their performance relies on transforming a complete input sequence - f
Externí odkaz:
http://arxiv.org/abs/2401.14267
Autor:
Cho, Young-Min, Pang, Dandan, Thapa, Stuti, Sherman, Garrick, Ungar, Lyle, Tay, Louis, Guntuku, Sharath Chandra
Although affective expressions of individuals have been extensively studied using social media, research has primarily focused on the Western context. There are substantial differences among cultures that contribute to their affective expressions. Th
Externí odkaz:
http://arxiv.org/abs/2401.05254