Zobrazeno 1 - 10
of 6 278
pro vyhledávání: '"Muralidharan, P"'
The zero-shot performance of object detectors degrades when tested on different modalities, such as infrared and depth. While recent work has explored image translation techniques to adapt detectors to new modalities, these methods are limited to a s
Externí odkaz:
http://arxiv.org/abs/2412.00622
Investigating the microscopic details of the proximity effect is crucial for both key experimental applications and fundamental inquiries into nanoscale devices featuring superconducting elements. In this work, we develop a framework motivated by exp
Externí odkaz:
http://arxiv.org/abs/2411.12733
This research work introduces a novel approach to the classification of Alzheimer's disease by using the advanced deep learning techniques combined with secure data processing methods. This research work primary uses transfer learning models such as
Externí odkaz:
http://arxiv.org/abs/2411.12756
The spin-valley or Kramers qubit promises significantly enhanced spin-valley lifetimes due to strong coupling of the electrons' spin to their momentum (valley) degrees of freedom. In transition metal dichalcogenides (TMDCs) such spin-valley locking i
Externí odkaz:
http://arxiv.org/abs/2410.21814
Autor:
Liu, Shih-Yang, Yang, Huck, Wang, Chien-Yi, Fung, Nai Chit, Yin, Hongxu, Sakr, Charbel, Muralidharan, Saurav, Cheng, Kwang-Ting, Kautz, Jan, Wang, Yu-Chiang Frank, Molchanov, Pavlo, Chen, Min-Hung
In this work, we re-formulate the model compression problem into the customized compensation problem: Given a compressed model, we aim to introduce residual low-rank paths to compensate for compression errors under customized requirements from users
Externí odkaz:
http://arxiv.org/abs/2410.21271
Autor:
Fang, Gongfan, Yin, Hongxu, Muralidharan, Saurav, Heinrich, Greg, Pool, Jeff, Kautz, Jan, Molchanov, Pavlo, Wang, Xinchao
Large Language Models (LLMs) are distinguished by their massive parameter counts, which typically result in significant redundancy. This work introduces MaskLLM, a learnable pruning method that establishes Semi-structured (or ``N:M'') Sparsity in LLM
Externí odkaz:
http://arxiv.org/abs/2409.17481
Autor:
Muralidharan, Varun, Cline, James M.
It has been proposed that the accelerated expansion of the universe can be explained by the merging of our universe with baby universes, resulting in dark energy with a phantom-like equation of state. However, the evidence in favor of it did not incl
Externí odkaz:
http://arxiv.org/abs/2408.13306
Autor:
Sreenivas, Sharath Turuvekere, Muralidharan, Saurav, Joshi, Raviraj, Chochowski, Marcin, Mahabaleshwarkar, Ameya Sunil, Shen, Gerald, Zeng, Jiaqi, Chen, Zijia, Suhara, Yoshi, Diao, Shizhe, Yu, Chenhan, Chen, Wei-Chun, Ross, Hayley, Olabiyi, Oluwatobi, Aithal, Ashwath, Kuchaiev, Oleksii, Korzekwa, Daniel, Molchanov, Pavlo, Patwary, Mostofa, Shoeybi, Mohammad, Kautz, Jan, Catanzaro, Bryan
We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation. We explore two distinct pruning strategies: (1) depth pruning and (2) joint hidden/at
Externí odkaz:
http://arxiv.org/abs/2408.11796
This project investigates the efficacy of Large Language Models (LLMs) in understanding and extracting scientific knowledge across specific domains and to create a deep learning framework: Knowledge AI. As a part of this framework, we employ pre-trai
Externí odkaz:
http://arxiv.org/abs/2408.04651
Autor:
Muralidharan, Saurav, Sreenivas, Sharath Turuvekere, Joshi, Raviraj, Chochowski, Marcin, Patwary, Mostofa, Shoeybi, Mohammad, Catanzaro, Bryan, Kautz, Jan, Molchanov, Pavlo
Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and then re-train
Externí odkaz:
http://arxiv.org/abs/2407.14679