Zobrazeno 1 - 10
of 64 332
pro vyhledávání: '"Sinha P. P."'
Autor:
Sinha, Sudip, Sinha, S.
We introduce the concept of ergodicity and explore its deviation caused by quantum scars in an isolated quantum system, employing a pedagogical approach based on a toy model. Quantum scars, originally identified as traces of classically unstable orbi
Externí odkaz:
http://arxiv.org/abs/2411.03234
Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data collection or re
Externí odkaz:
http://arxiv.org/abs/2412.06843
Autor:
Roy, Swarnava Sinha, Kundu, Ayan
Integrated Gradients is a well-known technique for explaining deep learning models. It calculates feature importance scores by employing a gradient based approach computing gradients of the model output with respect to input features and accumulating
Externí odkaz:
http://arxiv.org/abs/2412.03886
The blue loop stage of intermediate mass stars has been called a "magnifying glass", where even seemingly small effects in prior stages of evolution, as well as assumptions about stellar composition, rotation, and convection, produce discernible chan
Externí odkaz:
http://arxiv.org/abs/2412.03652
Bots constitute a significant portion of Internet traffic and are a source of various issues across multiple domains. Modern bots often become indistinguishable from real users, as they employ similar methods to browse the web, including using real b
Externí odkaz:
http://arxiv.org/abs/2412.02266
Test-driven development (TDD) is the practice of writing tests first and coding later, and the proponents of TDD expound its numerous benefits. For instance, given an issue on a source code repository, tests can clarify the desired behavior among sta
Externí odkaz:
http://arxiv.org/abs/2412.02883
Deep learning has achieved remarkable success in processing and managing unstructured data. However, its "black box" nature imposes significant limitations, particularly in sensitive application domains. While existing interpretable machine learning
Externí odkaz:
http://arxiv.org/abs/2412.01365
Autor:
Kolipaka, Varshita, Sinha, Akshit, Mishra, Debangan, Kumar, Sumit, Arun, Arvindh, Goel, Shashwat, Kumaraguru, Ponnurangam
Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distributed (i.i.d.) assumption, adversarial manipulations or incorrect data
Externí odkaz:
http://arxiv.org/abs/2412.00789
Decentralized Finance (DeFi) and smart contracts are the next generation and fast-growing market for quick and safe interaction between lenders and borrowers. However for maintaining a streamline ecosystem it is necessary to understand the risk assoc
Externí odkaz:
http://arxiv.org/abs/2412.00710
Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this hierarchy, treat
Externí odkaz:
http://arxiv.org/abs/2412.01023