Zobrazeno 1 - 10
of 13 263
pro vyhledávání: '"Donghyun An"'
Autor:
Lee, Donghyun, Tiwari, Mo
As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt injection
Externí odkaz:
http://arxiv.org/abs/2410.07283
Autor:
Hwang, Hochul, Suzuki, Ken, Giudice, Nicholas A, Biswas, Joydeep, Lee, Sunghoon Ivan, Kim, Donghyun
While guide dogs offer essential mobility assistance, their high cost, limited availability, and care requirements make them inaccessible to most blind or low vision (BLV) individuals. Recent advances in quadruped robots provide a scalable solution f
Externí odkaz:
http://arxiv.org/abs/2409.19778
Spiking Neural Networks (SNNs) present a compelling and energy-efficient alternative to traditional Artificial Neural Networks (ANNs) due to their sparse binary activation. Leveraging the success of the transformer architecture, the spiking transform
Externí odkaz:
http://arxiv.org/abs/2409.19764
Autor:
Kim, Jong-in, Lee, Donghyun
The Boltzmann equation is a fundamental equation in kinetic theory that describes the motion of rarefied gases. In this study, we examine the Boltzmann equation within a $C^1$ bounded domain, subject to a large external potential $\Phi(x)$ and diffus
Externí odkaz:
http://arxiv.org/abs/2409.16814
Robotic mobility aids for blind and low-vision (BLV) individuals rely heavily on deep learning-based vision models specialized for various navigational tasks. However, the performance of these models is often constrained by the availability and diver
Externí odkaz:
http://arxiv.org/abs/2409.11164
Autor:
Kim, Donghyun, Oh, Jaeseong
We introduce the Macdonald piece polynomial $\operatorname{I}_{\mu,\lambda,k}[X;q,t]$, which is a vast generalization of the Macdonald intersection polynomial in the science fiction conjecture by Bergeron and Garsia. We demonstrate a remarkable conne
Externí odkaz:
http://arxiv.org/abs/2409.01041
Spiking Neural Networks (SNNs) have emerged as a compelling, energy-efficient alternative to traditional Artificial Neural Networks (ANNs) for static image tasks such as image classification and segmentation. However, in the more complex video classi
Externí odkaz:
http://arxiv.org/abs/2409.01564
BGK (Bhatnagar-Gross-Krook) model is a relaxation-type model of the Boltzmann equation, which is popularly used in place of the Boltzmann equation in physics and engineering. In this paper, we address the ill-posedness problem for the BGK model, in w
Externí odkaz:
http://arxiv.org/abs/2408.08163
Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces genera
Externí odkaz:
http://arxiv.org/abs/2408.05749
Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to improve VL model
Externí odkaz:
http://arxiv.org/abs/2407.15296