Zobrazeno 1 - 10
of 135
pro vyhledávání: '"McGuire, Morgan"'
Autor:
Liu, Hsueh-Ti Derek, Agrawala, Maneesh, Yuksel, Cem, Omernick, Tim, Misra, Vinith, Corazza, Stefano, McGuire, Morgan, Zordan, Victor
This paper presents a unified differentiable boolean operator for implicit solid shape modeling using Constructive Solid Geometry (CSG). Traditional CSG relies on min, max operators to perform boolean operations on implicit shapes. But because these
Externí odkaz:
http://arxiv.org/abs/2407.10954
Toxicity classification for voice heavily relies on the semantic content of speech. We propose a novel framework that utilizes cross-modal learning to integrate the semantic embedding of text into a multilabel speech toxicity classifier during traini
Externí odkaz:
http://arxiv.org/abs/2406.10325
Autor:
Hirschkind, Nameer, Yu, Xiao, Nandwana, Mahesh Kumar, Liu, Joseph, DuBois, Eloi, Le, Dao, Thiebaut, Nicolas, Sinclair, Colin, Spence, Kyle, Shang, Charles, Abrams, Zoe, McGuire, Morgan
We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer component of
Externí odkaz:
http://arxiv.org/abs/2406.10223
Autor:
Xu, Pei, Xie, Kaixiang, Andrews, Sheldon, Kry, Paul G., Neff, Michael, McGuire, Morgan, Karamouzas, Ioannis, Zordan, Victor
Publikováno v:
ACM Transactions on Graphics 42, 6, Article 112.1522 (December 2023)
Motivated by humans' ability to adapt skills in the learning of new ones, this paper presents AdaptNet, an approach for modifying the latent space of existing policies to allow new behaviors to be quickly learned from like tasks in comparison to lear
Externí odkaz:
http://arxiv.org/abs/2310.00239
Autor:
Dugan, Liam, Wadhawan, Anshul, Spence, Kyle, Callison-Burch, Chris, McGuire, Morgan, Zordan, Victor
Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In latency-sensitive
Externí odkaz:
http://arxiv.org/abs/2306.01201
Autor:
Takikawa, Towaki, Evans, Alex, Tremblay, Jonathan, Müller, Thomas, McGuire, Morgan, Jacobson, Alec, Fidler, Sanja
Neural approximations of scalar and vector fields, such as signed distance functions and radiance fields, have emerged as accurate, high-quality representations. State-of-the-art results are obtained by conditioning a neural approximation with a look
Externí odkaz:
http://arxiv.org/abs/2206.07707
Autor:
Spjut, Josef, Zhu, Fengyuan, Huang, Xiaolei, Shou, Yichen, Boudaoud, Ben, Shapira, Omer, McGuire, Morgan
Augmented Reality (AR) is an emerging field ripe for experimentation, especially when it comes to developing the kinds of applications and experiences that will drive mass adoption of the technology. While we aren't aware of any current consumer prod
Externí odkaz:
http://arxiv.org/abs/2202.06726
In the emerging field of esports research, there is an increasing demand for quantitative results that can be used by players, coaches and analysts to make decisions and present meaningful commentary for spectators. We present FirstPersonScience, a s
Externí odkaz:
http://arxiv.org/abs/2202.06429
Order-independent transparency schemes rely on low-order approximations of transmittance as a function of depth. We introduce a new wavelet representation of this function and an algorithm for building and evaluating it efficiently on a GPU. We then
Externí odkaz:
http://arxiv.org/abs/2201.00094