Zobrazeno 1 - 10
of 2 223
pro vyhledávání: '"LUNING, P. A."'
Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache compression me
Externí odkaz:
http://arxiv.org/abs/2409.10593
Deep neural networks (DNNs) have significantly boosted the performance of many challenging tasks. Despite the great development, DNNs have also exposed their vulnerability. Recent studies have shown that adversaries can manipulate the predictions of
Externí odkaz:
http://arxiv.org/abs/2408.01715
Autor:
Zhou, Zixuan, Ning, Xuefei, Hong, Ke, Fu, Tianyu, Xu, Jiaming, Li, Shiyao, Lou, Yuming, Wang, Luning, Yuan, Zhihang, Li, Xiuhong, Yan, Shengen, Dai, Guohao, Zhang, Xiao-Ping, Dong, Yuhan, Wang, Yu
Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in resource-const
Externí odkaz:
http://arxiv.org/abs/2404.14294
Autor:
Zhang, Harry, Caldararu, Stefan, Young, Aaron, Ruiz, Alexis, Unjhawala, Huzaifa, Mahajan, Ishaan, Ashokkumar, Sriram, Batagoda, Nevindu, Zhou, Zhenhao, Bakke, Luning, Negrut, Dan
We report results obtained and insights gained while answering the following question: how effective is it to use a simulator to establish path following control policies for an autonomous ground robot? While the quality of the simulator conditions t
Externí odkaz:
http://arxiv.org/abs/2403.18021
Autor:
Li, Shiyao, Ning, Xuefei, Wang, Luning, Liu, Tengxuan, Shi, Xiangsheng, Yan, Shengen, Dai, Guohao, Yang, Huazhong, Wang, Yu
Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs. To meet the requirement
Externí odkaz:
http://arxiv.org/abs/2402.18158
Autor:
Lubinski, Thomas, Goings, Joshua J., Mayer, Karl, Johri, Sonika, Reddy, Nithin, Mehta, Aman, Bhatia, Niranjan, Rappaport, Sonny, Mills, Daniel, Baldwin, Charles H., Zhao, Luning, Barbosa, Aaron, Maity, Smarak, Mundada, Pranav S.
The QED-C suite of Application-Oriented Benchmarks provides the ability to gauge performance characteristics of quantum computers as applied to real-world applications. Its benchmark programs sweep over a range of problem sizes and inputs, capturing
Externí odkaz:
http://arxiv.org/abs/2402.08985
Autor:
Zhao, Luning, Goings, Joshua, Wang, Qingfeng, Shin, Kyujin, Kyoung, Woomin, Noh, Seunghyo, Rhee, Young Min, Kim, Kyungmin
The electron pair approximation offers a resource efficient variational quantum eigensolver (VQE) approach for quantum chemistry simulations on quantum computers. With the number of entangling gates scaling quadratically with system size and a consta
Externí odkaz:
http://arxiv.org/abs/2312.05426
Turbulent flows have historically presented formidable challenges to predictive computational modeling. Traditional numerical simulations often require vast computational resources, making them infeasible for numerous engineering applications. As an
Externí odkaz:
http://arxiv.org/abs/2311.07896
Autor:
Zhang, Ruochun, Tagliafierro, Bonaventura, Heuvel, Colin Vanden, Sabarwal, Shlok, Bakke, Luning, Yue, Yulong, Wei, Xin, Serban, Radu, Negrut, Dan
This paper introduces DEM-Engine, a new submodule of Project Chrono, that is designed to carry out Discrete Element Method (DEM) simulations. Based on spherical primitive shapes, DEM-Engine can simulate polydisperse granular materials and handle comp
Externí odkaz:
http://arxiv.org/abs/2311.04648
Autor:
Dimitrov, Emil, Sanchez-Sanz, Goar, Nelson, James, O'Riordan, Lee, Doyle, Myles, Courtney, Sean, Kannan, Venkatesh, Naseri, Hassan, Garcia, Alberto Garcia, Tricker, James, Faraggi, Marisa, Goings, Joshua, Zhao, Luning
Accurate and scalable methods for computational quantum chemistry can accelerate research and development in many fields, ranging from drug discovery to advanced material design. Solving the electronic Schrodinger equation is the core problem of comp
Externí odkaz:
http://arxiv.org/abs/2311.01242