Zobrazeno 1 - 10
of 311
pro vyhledávání: '"Nair, Lakshmi P."'
Autor:
Nair, Lakshmi
Synthetic data generation is an important application of machine learning in the field of medical imaging. While existing approaches have successfully applied fine-tuned diffusion models for synthesizing medical images, we explore potential improveme
Externí odkaz:
http://arxiv.org/abs/2410.00731
We advocate for a strong integration of Computational Creativity (CC) with research in large language and vision models (LLVMs) to address a key limitation of these models, i.e., creative problem solving. We present preliminary experiments showing ho
Externí odkaz:
http://arxiv.org/abs/2405.01453
Autor:
Nair, Lakshmi
Publikováno v:
Extended abstract: 28th IEEE High Performance Extreme Computing Conference (HPEC) 2024 - Outstanding short paper award
Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as teachers. Typ
Externí odkaz:
http://arxiv.org/abs/2404.06170
Autor:
Nair, Lakshmi, Widemann, David, Turcott, Brad, Moore, Nick, Wleklinski, Alexandra, Bunandar, Darius, Papavasileiou, Ioannis, Wang, Shihu, Logan, Eric
Photonic computing promises faster and more energy-efficient deep neural network (DNN) inference than traditional digital hardware. Advances in photonic computing can have profound impacts on applications such as autonomous driving and defect detecti
Externí odkaz:
http://arxiv.org/abs/2309.16783
Analog computing has reemerged as a promising avenue for accelerating deep neural networks (DNNs) due to its potential to overcome the energy efficiency and scalability challenges posed by traditional digital architectures. However, achieving high pr
Externí odkaz:
http://arxiv.org/abs/2309.10759
Autor:
Nair, Lakshmi, Bernadskiy, Mikhail, Madhavan, Arulselvan, Chan, Craig, Basumallik, Ayon, Bunandar, Darius
The recent rise of large language models (LLMs) has resulted in increased efforts towards running LLMs at reduced precision. Running LLMs at lower precision supports resource constraints and furthers their democratization, enabling users to run billi
Externí odkaz:
http://arxiv.org/abs/2307.03712
Autor:
Nair, Lakshmi, Bunandar, Darius
Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational costs, even when starting from
Externí odkaz:
http://arxiv.org/abs/2306.03076
Autor:
Basumallik, Ayon, Bunandar, Darius, Dronen, Nicholas, Harris, Nicholas, Levkova, Ludmila, McCarter, Calvin, Nair, Lakshmi, Walter, David, Widemann, David
Analog mixed-signal (AMS) devices promise faster, more energy-efficient deep neural network (DNN) inference than their digital counterparts. However, recent studies show that DNNs on AMS devices with fixed-point numbers can incur an accuracy penalty
Externí odkaz:
http://arxiv.org/abs/2205.06287
Publikováno v:
Journal of Artificial Intelligence Research 2022
Creative Problem Solving (CPS) is a sub-area within Artificial Intelligence (AI) that focuses on methods for solving off-nominal, or anomalous problems in autonomous systems. Despite many advancements in planning and learning, resolving novel problem
Externí odkaz:
http://arxiv.org/abs/2204.10358
Requiring multiple demonstrations of a task plan presents a burden to end-users of robots. However, robustly executing tasks plans from a single end-user demonstration is an ongoing challenge in robotics. We address the problem of one-shot task execu
Externí odkaz:
http://arxiv.org/abs/2105.04484