Zobrazeno 1 - 10
of 48
pro vyhledávání: '"TULI, SHIKHAR"'
Autor:
Lin, Chi-Heng, Gao, Shangqian, Smith, James Seale, Patel, Abhishek, Tuli, Shikhar, Shen, Yilin, Jin, Hongxia, Hsu, Yen-Chang
Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices with limit
Externí odkaz:
http://arxiv.org/abs/2408.09632
Traditional language models operate autoregressively, i.e., they predict one token at a time. Rapid explosion in model sizes has resulted in high inference times. In this work, we propose DynaMo, a suite of multi-token prediction language models that
Externí odkaz:
http://arxiv.org/abs/2405.00888
Autor:
Tuli, Shikhar, Jha, Niraj K.
Researchers constantly strive to explore larger and more complex search spaces in various scientific studies and physical experiments. However, such investigations often involve sophisticated simulators or time-consuming experiments that make explori
Externí odkaz:
http://arxiv.org/abs/2308.08666
Autor:
Tuli, Shikhar, Jha, Niraj K.
Automated co-design of machine learning models and evaluation hardware is critical for efficiently deploying such models at scale. Despite the state-of-the-art performance of transformer models, they are not yet ready for execution on resource-constr
Externí odkaz:
http://arxiv.org/abs/2303.14882
Autor:
Tuli, Shikhar, Jha, Niraj K.
Automated design of efficient transformer models has recently attracted significant attention from industry and academia. However, most works only focus on certain metrics while searching for the best-performing transformer architecture. Furthermore,
Externí odkaz:
http://arxiv.org/abs/2303.13745
Autor:
Tuli, Shikhar, Jha, Niraj K.
Self-attention-based transformer models have achieved tremendous success in the domain of natural language processing. Despite their efficacy, accelerating the transformer is challenging due to its quadratic computational complexity and large activat
Externí odkaz:
http://arxiv.org/abs/2302.14705
Recently, automated co-design of machine learning (ML) models and accelerator architectures has attracted significant attention from both the industry and academia. However, most co-design frameworks either explore a limited search space or employ su
Externí odkaz:
http://arxiv.org/abs/2212.03965
The existence of a plethora of language models makes the problem of selecting the best one for a custom task challenging. Most state-of-the-art methods leverage transformer-based models (e.g., BERT) or their variants. Training such models and explori
Externí odkaz:
http://arxiv.org/abs/2205.11656
In standard generative deep learning models, such as autoencoders or GANs, the size of the parameter set is proportional to the complexity of the generated data distribution. A significant challenge is to deploy resource-hungry deep learning models i
Externí odkaz:
http://arxiv.org/abs/2110.02912
Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function found by a mac
Externí odkaz:
http://arxiv.org/abs/2105.07197