Zobrazeno 1 - 10
of 7 195
pro vyhledávání: '"Sudarshan, P."'
Autor:
Svanidze, Anastasiia, Kundu, Sudarshan, Iadlovska, Olena, Thakur, Anil K., Zheng, Xiaoyu, Palffy-Muhoray, Peter
Azo-containing liquid crystal elatomers are photomechanical materials which can be actuated by illumination. The photomechanical response is a result of the photoisomerization of the azo moiety, which produces bulk stresses in the material. These str
Externí odkaz:
http://arxiv.org/abs/2412.05791
All-weather image restoration (AWIR) is crucial for reliable autonomous navigation under adverse weather conditions. AWIR models are trained to address a specific set of weather conditions such as fog, rain, and snow. But this causes them to often st
Externí odkaz:
http://arxiv.org/abs/2411.17814
Deep learning-based models for All-In-One Image Restoration (AIOR) have achieved significant advancements in recent years. However, their practical applicability is limited by poor generalization to samples outside the training distribution. This lim
Externí odkaz:
http://arxiv.org/abs/2411.17687
We propose a new approach for fine-grained uncertainty quantification (UQ) using a collision matrix. For a classification problem involving $K$ classes, the $K\times K$ collision matrix $S$ measures the inherent (aleatoric) difficulty in distinguishi
Externí odkaz:
http://arxiv.org/abs/2411.12127
Autor:
Regmi, Sudarshan
Out-of-distribution (OOD) detection is critical to ensure the safe deployment of deep learning models in critical applications. Deep learning models can often misidentify OOD samples as in-distribution (ID) samples. This vulnerability worsens in the
Externí odkaz:
http://arxiv.org/abs/2411.10794
Autor:
Kang, Beomseok, Saha, Priyabrata, Sharma, Sudarshan, Chakraborty, Biswadeep, Mukhopadhyay, Saibal
We introduce a novel framework, Online Relational Inference (ORI), designed to efficiently identify hidden interaction graphs in evolving multi-agent interacting systems using streaming data. Unlike traditional offline methods that rely on a fixed tr
Externí odkaz:
http://arxiv.org/abs/2411.01442
Autor:
Ananth, Sudarshan, Bhave, Nipun
We construct maximal supergravity in five-dimensions by 'oxidizing' the four-dimensional $\mathcal{N}=8$ theory. The relevant symmetries, the unitary symplectic group $USp(8)$ and the exceptional group $E_6$, are both presented in light-cone superspa
Externí odkaz:
http://arxiv.org/abs/2410.19463
This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in creating word-lev
Externí odkaz:
http://arxiv.org/abs/2410.18215
Autor:
Harithas, Sudarshan, Sridhar, Srinath
This paper introduces MotionGlot, a model that can generate motion across multiple embodiments with different action dimensions, such as quadruped robots and human bodies. By leveraging the well-established training procedures commonly used in large
Externí odkaz:
http://arxiv.org/abs/2410.16623
Autor:
Bhardwaj, Ankit, Balashankar, Ananth, Iyer, Shiva, Soans, Nita, Sudarshan, Anant, Pande, Rohini, Subramanian, Lakshminarayanan
Urban air pollution hotspots pose significant health risks, yet their detection and analysis remain limited by the sparsity of public sensor networks. This paper addresses this challenge by combining predictive modeling and mechanistic approaches to
Externí odkaz:
http://arxiv.org/abs/2410.04309