Zobrazeno 1 - 10
of 473
pro vyhledávání: '"Banerjee, Soumya"'
Diffusion-based models demonstrate impressive generation capabilities. However, they also have a massive number of parameters, resulting in enormous model sizes, thus making them unsuitable for deployment on resource-constraint devices. Block-wise ge
Externí odkaz:
http://arxiv.org/abs/2408.17095
Autor:
Ahamed, Sayyed Farid, Banerjee, Soumya, Roy, Sandip, Quinn, Devin, Vucovich, Marc, Choi, Kevin, Rahman, Abdul, Hu, Alison, Bowen, Edward, Shetty, Sachin
Over the last few years, federated learning (FL) has emerged as a prominent method in machine learning, emphasizing privacy preservation by allowing multiple clients to collaboratively build a model while keeping their training data private. Despite
Externí odkaz:
http://arxiv.org/abs/2407.19119
Autor:
Bober-Irizar, Mikel, Banerjee, Soumya
For half a century, artificial intelligence research has attempted to reproduce the human qualities of abstraction and reasoning - creating computer systems that can learn new concepts from a minimal set of examples, in settings where humans find thi
Externí odkaz:
http://arxiv.org/abs/2402.03507
Autor:
VenkataKeerthy, S., Banerjee, Soumya, Dey, Sayan, Andaluri, Yashas, PS, Raghul, Kalyanasundaram, Subrahmanyam, Pereira, Fernando Magno Quintão, Upadrasta, Ramakrishna
Binary similarity involves determining whether two binary programs exhibit similar functionality, often originating from the same source code. In this work, we propose VexIR2Vec, an approach for binary similarity using VEX-IR, an architecture-neutral
Externí odkaz:
http://arxiv.org/abs/2312.00507
Autor:
Banerjee, Soumya, Sanyal, Debarshi Kumar, Chattopadhyay, Samiran, Bhowmick, Plaban Kumar, Das, Partha Pratim
Digital libraries often face the challenge of processing a large volume of diverse document types. The manual collection and tagging of metadata can be a time-consuming and error-prone task. To address this, we aim to develop an automatic metadata ex
Externí odkaz:
http://arxiv.org/abs/2401.12220
An end-to-end fiber-based network holds the potential to provide multi-gigabit fixed access to end-users. However, deploying fiber access, especially in areas where fiber is non-existent, can be time-consuming and costly, resulting in delayed returns
Externí odkaz:
http://arxiv.org/abs/2312.09467
Autor:
Banerjee, Soumya, Roy, Sandip, Ahamed, Sayyed Farid, Quinn, Devin, Vucovich, Marc, Nandakumar, Dhruv, Choi, Kevin, Rahman, Abdul, Bowen, Edward, Shetty, Sachin
The membership inference attack (MIA) is a popular paradigm for compromising the privacy of a machine learning (ML) model. MIA exploits the natural inclination of ML models to overfit upon the training data. MIAs are trained to distinguish between tr
Externí odkaz:
http://arxiv.org/abs/2312.00051
Autor:
Banerjee, Soumya, Verma, Vinay K., Mukherjee, Avideep, Gupta, Deepak, Namboodiri, Vinay P., Rai, Piyush
Lifelong learning or continual learning is the problem of training an AI agent continuously while also preventing it from forgetting its previously acquired knowledge. Streaming lifelong learning is a challenging setting of lifelong learning with the
Externí odkaz:
http://arxiv.org/abs/2309.08227
Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed in a rapidl
Externí odkaz:
http://arxiv.org/abs/2301.11892
Autor:
Bober-Irizar, Mikel1 (AUTHOR), Banerjee, Soumya1 (AUTHOR) sb2333@cam.ac.uk
Publikováno v:
Scientific Reports. 11/16/2024, Vol. 14 Issue 1, p1-20. 20p.
