Zobrazeno 1 - 10
of 445
pro vyhledávání: '"Saha Amrita"'
Autor:
Salaam Ahmed, Thakur Sandeep, Prajapati Bhavin Kumar, Davala Karunakumar, Rajalakshmi B., Nijhawan Ginni, Saha Amrita
Publikováno v:
E3S Web of Conferences, Vol 552, p 01092 (2024)
There are different medical applications that utilize biomaterials to settle tissues, convey drugs, and make biomedical devices. This paper gives a relevant analysis of biomaterials talking about their groupings, highlights, biocompatibility issues,
Externí odkaz:
https://doaj.org/article/33fea266ff684e5b91a24321e77b298e
Autor:
Xu, Yuhui, Jie, Zhanming, Dong, Hanze, Wang, Lei, Lu, Xudong, Zhou, Aojun, Saha, Amrita, Xiong, Caiming, Sahoo, Doyen
Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications by leveraging increased model sizes and sequence lengths. However, the associated rise in
Externí odkaz:
http://arxiv.org/abs/2407.21018
With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Previous distillation methods usually prompt ChatGPT to generate a set of
Externí odkaz:
http://arxiv.org/abs/2310.18628
Large Language Models (LLMs) have already become quite proficient at solving simpler programming tasks like those in HumanEval or MBPP benchmarks. However, solving more complex and competitive programming tasks is still quite challenging for these mo
Externí odkaz:
http://arxiv.org/abs/2310.08992
Autor:
Cheng, Qian, Sahoo, Doyen, Saha, Amrita, Yang, Wenzhuo, Liu, Chenghao, Woo, Gerald, Singh, Manpreet, Saverese, Silvio, Hoi, Steven C. H.
Artificial Intelligence for IT operations (AIOps) aims to combine the power of AI with the big data generated by IT Operations processes, particularly in cloud infrastructures, to provide actionable insights with the primary goal of maximizing availa
Externí odkaz:
http://arxiv.org/abs/2304.04661
Software and System logs record runtime information about processes executing within a system. These logs have become the most critical and ubiquitous forms of observability data that help developers understand system behavior, monitor system health
Externí odkaz:
http://arxiv.org/abs/2301.13415
Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text classification in
Externí odkaz:
http://arxiv.org/abs/2211.17142
Autor:
Saha, Amrita, author, Castro, André, author, Carreras, Marco, author, Guariso, Daniele, author
Publikováno v:
Sustaining Tanzania's Economic Development : A Firm and Household Perspective, 2024.
Externí odkaz:
https://doi.org/10.1093/oso/9780192885746.003.0004
Prompt Tuning has been largely successful as a parameter-efficient method of conditioning large-scale pre-trained language models to perform downstream tasks. Thus far, soft prompt tuning learns a fixed set of task-specific continuous vectors, i.e.,
Externí odkaz:
http://arxiv.org/abs/2205.11024
Autor:
Saha, Amrita, Hoi, Steven C. H.
Publikováno v:
ICSE-SEIP 2022
Root Cause Analysis (RCA) of any service-disrupting incident is one of the most critical as well as complex tasks in IT processes, especially for cloud industry leaders like Salesforce. Typically RCA investigation leverages data-sources like applicat
Externí odkaz:
http://arxiv.org/abs/2204.11598