Zobrazeno 1 - 10
of 3 212
pro vyhledávání: '"Arefin, A."'
Autor:
Arefin, Md Rifat, Subbaraj, Gopeshh, Gontier, Nicolas, LeCun, Yann, Rish, Irina, Shwartz-Ziv, Ravid, Pal, Christopher
Decoder-only Transformers often struggle with complex reasoning tasks, particularly arithmetic reasoning requiring multiple sequential operations. In this work, we identify representation collapse in the model's intermediate layers as a key factor li
Externí odkaz:
http://arxiv.org/abs/2411.02344
Autor:
Arefin, Nirob
Generative Adversarial Networks (GAN) are among the widely used Generative models in various applications. However, the original GAN architecture may memorize the distribution of the training data and, therefore, poses a threat to Membership Inferenc
Externí odkaz:
http://arxiv.org/abs/2410.07803
Autor:
Arefin, Sayed Erfan, Serwadda, Abdul
Modern computers rely on USB and HDMI ports for connecting external peripherals and display devices. Despite their built-in security measures, these ports remain susceptible to passive power-based side-channel attacks. This paper presents a new class
Externí odkaz:
http://arxiv.org/abs/2410.02539
Machine learning models often struggle with distribution shifts in real-world scenarios, whereas humans exhibit robust adaptation. Models that better align with human perception may achieve higher out-of-distribution generalization. In this study, we
Externí odkaz:
http://arxiv.org/abs/2409.05817
Crowd density level estimation is an essential aspect of crowd safety since it helps to identify areas of probable overcrowding and required conditions. Nowadays, AI systems can help in various sectors. Here for safety purposes or many for public ser
Externí odkaz:
http://arxiv.org/abs/2405.07419
Autor:
Kowsher, Md., Panditi, Ritesh, Prottasha, Nusrat Jahan, Bhat, Prakash, Bairagi, Anupam Kumar, Arefin, Mohammad Shamsul
Conversational modeling using Large Language Models (LLMs) requires a nuanced understanding of context to generate coherent and contextually relevant responses. In this paper, we present Token Trails, a novel approach that leverages token-type embedd
Externí odkaz:
http://arxiv.org/abs/2404.02402
Autor:
Arefin, Md Rifat, Zhang, Yan, Baratin, Aristide, Locatello, Francesco, Rish, Irina, Liu, Dianbo, Kawaguchi, Kenji
Publikováno v:
ICLM 2024
Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotation to remove spurious correlat
Externí odkaz:
http://arxiv.org/abs/2402.13368
Publikováno v:
Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 8, 1, Article 3 (March 2024), 29 pages
Small form factor limits physical input space in earable (i.e., ear-mounted wearable) devices. Off-device earable inputs in alternate mid-air and on-skin around-ear interaction spaces using uni-manual gestures can address this input space limitation.
Externí odkaz:
http://arxiv.org/abs/2401.17605
A generalized additive mixed model was estimated to investigate the factors that impact ridehailing driver trip request acceptance choices, relying on 200 responses from a stated preference survey in Seattle, US. Several policy recommendations were p
Externí odkaz:
http://arxiv.org/abs/2402.01650
Recently, extended reality (XR) displays including augmented reality (AR) and virtual reality (VR) have integrated eye tracking capabilities, which could enable novel ways of interacting with XR content. The vergence angle of the eyes constantly chan
Externí odkaz:
http://arxiv.org/abs/2311.09242