Rishabh Gupta

ORCID: 0000-0001-8634-6819
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Natural Language Processing Techniques
  • Blockchain Technology Applications and Security
  • Software Engineering Research
  • Quantum Computing Algorithms and Architecture
  • Market Dynamics and Volatility
  • Multimodal Machine Learning Applications
  • Text Readability and Simplification
  • Cloud Data Security Solutions
  • IoT and Edge/Fog Computing
  • Quantum many-body systems
  • Semiconductor materials and devices
  • Advancements in Semiconductor Devices and Circuit Design
  • Privacy-Preserving Technologies in Data
  • Monetary Policy and Economic Impact
  • Air Quality and Health Impacts
  • Speech and dialogue systems
  • Pelvic and Acetabular Injuries
  • Information and Cyber Security
  • Cloud Computing and Remote Desktop Technologies
  • Maritime Ports and Logistics
  • Expert finding and Q&A systems
  • Adversarial Robustness in Machine Learning
  • Management, Economics, and Public Policy
  • Semantic Web and Ontologies

Indraprastha Institute of Information Technology Delhi
2015-2023

Indian Institute of Technology Delhi
2015-2023

University of Petroleum and Energy Studies
2023

Badan Penelitian dan Pengembangan Kesehatan
2023

Guru Gobind Singh Indraprastha University
2023

National Sun Yat-sen University
2023

National Institute of Technology Kurukshetra
2023

Galgotias University
2022

Manipal University Jaipur
2022

North Oaks Health System
2022

This article explores the critical aspects of securing distributed systems within government and public sector organizations. It examines implementation comprehensive security frameworks, including Zero Trust Architecture, Artificial Intelligence-driven threat detection, advanced identity management solutions. The discusses challenges faced by federal agencies in protecting sensitive data across interconnected while maintaining operational efficiency. addresses key areas verification,...

10.32628/cseit25112378 article EN International Journal of Scientific Research in Computer Science Engineering and Information Technology 2025-03-04
Kaustubh Dhole Varun Gangal Sebastian Gehrmann Aadesh Gupta Zhenhao Li and 95 more Saad Mahamood Abinaya Mahendiran Simon Mille Ashish Shrivastava Samson Tan Tongshuang Wu Jascha Sohl‐Dickstein Jinho D. Choi Eduard Hovy Ondřej Dušek Sebastian Ruder Sajant Anand Nagender Aneja Rabin Banjade Lisa Barthe Hanna Behnke Ian Berlot-Attwell Connor Boyle Caroline Brun Marco Antonio Sobrevilla Cabezudo Samuel Cahyawijaya Émile Chapuis Wanxiang Che Mukund Choudhary Christian Clauss Pierre Colombo Filip Cornell Gautier Dagan Mayukh Das Tanay Dixit Thomas Dopierre Paul-Alexis Dray Suchitra Dubey Tatiana Ekeinhor Marco Di Giovanni Tanya Goyal Rishabh Gupta Rishabh Gupta Louanes Hamla Sang Wook Han Fabrice Harel-Canada Antoine Honoré Ishan Jindal Przemyslaw K. Joniak Denis Kleyko Venelin Kovatchev Kalpesh Krishna Ashutosh Kumar Stefan Langer Seungjae Ryan Lee Corey James Levinson Hualou Liang Kaizhao Liang Zhexiong Liu Andrey Lukyanenko Vukosi Marivate Gerard de Melo Simon Méoni Maxime Meyer Afnan Mir Nafise Sadat Moosavi Niklas Muennighoff Timothy Sum Hon Mun Kenton Murray Marcin Namysł Maria Obedkova Priti Oli Nivranshu Pasricha Jan Pfister Richard Plant Vinay Prabhu Vasile Păiș Libo Qin Shahab Raji Pawan Kumar Rajpoot Vikas Raunak Roy Rinberg Nicolas Roberts Juan Diego Rodríguez Claude Roux P. H. S. Vasconcellos Ananya B. Sai Robin M. Schmidt Thomas Scialom Tshephisho Joseph Sefara Saqib Shamsi Xudong Shen Haoyue Shi Yiwen Shi Анна Швец Nick Siegel Damien Sileo Jamie Simon Chandan Singh Roman Sitelew

Data augmentation is an important component in the robustness evaluation of models natural language processing (NLP) and enhancing diversity data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based framework which supports creation both transformations (modifications to data) filters (data splits according specific features). We describe initial set 117 23 for variety tasks. demonstrate efficacy NL-Augmenter by using several its analyze popular...

10.48550/arxiv.2112.02721 preprint EN cc-by arXiv (Cornell University) 2021-01-01

Air pollution has a wide range of implications on agriculture, economy, road accidents, and health. In this paper, we use novel deep learning methods for short-term (multi-step-ahead) air-quality prediction in selected parts Delhi, India. Our comprise long memory (LSTM) network models which also include some recent versions such as bidirectional-LSTM encoder-decoder LSTM models. We multivariate time series approach that attempts to predict air quality 10 horizons covering total 80 hours...

10.48550/arxiv.2102.10551 preprint EN cc-by-nc-nd arXiv (Cornell University) 2021-01-01
Kaustubh Dhole Varun Gangal Sebastian Gehrmann Aadesh Gupta Zhenhao Li and 95 more Saad Mahamood Abinaya Mahadiran Simon Mille Ashish Shrivastava Samson Tan Tongshang Wu Jascha Sohl‐Dickstein Jinho Choi Eduard Hovy Ondřej Dušek Sebastian Ruder Sajant Anand Nagender Aneja Rabin Banjade Lisa Barthe Hanna Behnke Ian Berlot-Attwell Connor Boyle Caroline Brun Marco Antonio Sobrevilla Cabezudo Samuel Cahyawijaya Émile Chapuis Wanxiang Che Mukund Choudhary Christian Clauss Pierre Colombo Filip Cornell Gautier Dagan Mayukh Das Tanay Dixit Thomas Dopierre Paul-Alexis Dray Suchitra Dubey Tatiana Ekeinhor Marco Di Giovanni Tanya Goyal Rishabh Gupta Louanes Hamla Sang Wook Han Fabrice Harel-Canada Antoine Honoré Ishan Jindal Przemysław Joniak Denis Kleyko Venelin Kovatchev Kalpesh Krishna Ashutosh Kumar Stefan Langer Seungjae Ryan Lee Corey James Levinson Hualou Liang Kaizhao Liang Zhexiong Liu Andrey Lukyanenko Vukosi Marivate Gerard de Melo Simon Méoni Maxine Meyer Afnan Mir Nafise Sadat Moosavi Niklas Meunnighoff Timothy Sum Hon Mun Kenton Murray Marcin Namysł Maria Obedkova Priti Oli Nivranshu Pasricha Jan Pfister Richard E. Plant Vinay Prabhu Vasile Păiș Libo Qin Shahab Raji Pawan Kumar Rajpoot Vikas Raunak Roy Rinberg Nicholas J. Roberts Juan Diego Rodríguez Claude Roux Vasconcellos Samus Ananya B. Sai Robin Schmidt Thomas Scialom Tshephisho Joseph Sefara Saqib Shamsi Xudong Shen Yiwen Shi Haoyue Shi Анна Швец Nick Siegel Damien Sileo Jamie Simon Chandan Singh Roman Sitelew Priyank Soni

Data augmentation is an important method for evaluating the robustness of and enhancing diversity training data natural language processing (NLP) models. In this paper, we present NL-Augmenter, a new participatory Python-based (NL) framework which supports creation transformations (modifications to data) filters (data splits according specific features). We describe initial set 117 23 variety NL tasks annotated with noisy descriptive tags. The incorporate noise, intentional accidental human...

10.3384/nejlt.2000-1533.2023.4725 article EN Northern European Journal of Language Technology 2023-04-08

Millions of users across the world leverages data processing and sharing benefits from cloud environment. Data security privacy are inevitable requirement Massive usage among opens door to loopholes. This paper envisages a discussion environment, its utilities, challenges, emerging research trends confined secure data.

10.48550/arxiv.2108.09508 preprint EN cc-by-sa arXiv (Cornell University) 2021-01-01

<p>This letter proposes a novel malicious user prediction model based on quantum machine learning that estimates the vicious entity present in communication system precedently before allocating data distributed environments. The proposed scrutinizes behavior of each and probable breaches using developed predictor unit. computes essential scores associated with request for process unit by generating training samples. exploits computational behavioral properties Qubits Quantum gates...

10.36227/techrxiv.21780695 preprint EN cc-by 2023-01-24

Rishabh Gupta, Shaily Desai, Manvi Goel, Anil Bandhakavi, Tanmoy Chakraborty, Md. Shad Akhtar. Proceedings of the 61st Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2023.

10.18653/v1/2023.acl-long.318 article EN cc-by 2023-01-01

Continuous technology scaling and the growing trend of low power applications have led to focus on ultra voltage operating memories. This work presents a report different configurations SRAM cells (6T 10T) operate in sub-threshold region.

10.1109/icacea.2015.7164763 article EN International Conference on Advances in Computer Engineering and Applications 2015-03-01

Automating code documentation through explanatory text can prove highly beneficial in understanding. Large Language Models (LLMs) have made remarkable strides Natural Processing, especially within software engineering tasks such as generation and summarization. This study specifically delves into the task of generating natural-language summaries for snippets, using various LLMs. The findings indicate that Code LLMs outperform their generic counterparts, zero-shot methods yield superior...

10.48550/arxiv.2310.16673 preprint EN cc-by arXiv (Cornell University) 2023-01-01

Code explanation plays a crucial role in the software engineering domain, aiding developers grasping code functionality efficiently. Recent work shows that performance of LLMs for improves few-shot setting, especially when examples are selected intelligently. State-of-the-art approaches such Selective Shot Learning (SSL) include token-based and embedding-based methods. However, these SSL have been evaluated on proprietary LLMs, without much exploration open-source Code-LLMs. Additionally,...

10.48550/arxiv.2412.12852 preprint EN arXiv (Cornell University) 2024-12-17

Computation of document similarity is a critical task in various NLP domains that has applications deduplication, matching, and recommendation. Traditional approaches for computation include learning representations documents employing or distance function over the embeddings. However, pairwise similarities differences are not efficiently captured by individual representations. Graph such as Joint Concept Interaction (JCIG) represent pair joint undirected weighted graph. JCIGs facilitate an...

10.48550/arxiv.2402.03957 preprint EN arXiv (Cornell University) 2024-02-06

10.1016/j.cstp.2023.100993 article EN Case Studies on Transport Policy 2023-03-20

Semantic Noise affects text analytics activities for the domain-specific industries significantly. It impedes understanding which holds prime importance in critical decision making tasks. In this work, we formalize semantic noise as a sequence of terms that do not contribute to narrative text. We look beyond notion standard statistically-based stop words and consider semantics exclude noise. present novel Infusion technique associate meta-data with categorical corpus demonstrate its...

10.48550/arxiv.2002.02238 preprint EN cc-by-nc-sa arXiv (Cornell University) 2020-01-01

Nowadays, more and machine learning applications, such as medical diagnosis, online fraud detection, email spam filtering, etc., services are provided by cloud computing. The service provider collects the data from various owners to train or classify system in environment. However, multiple may not entirely rely on platform that a third party engages. Therefore, security privacy problems among critical hindrances using tools, particularly with owners. In addition, unauthorized entities can...

10.48550/arxiv.2211.13542 preprint EN cc-by arXiv (Cornell University) 2022-01-01

Real estate companies keep special care when they purchase or sell a new house. A significant amount of expertise and market awareness is required for making accurate price predictions houses so as to turn it out into profitable investment. Also, the setting prices manually quite difficult tedious task accuracy prediction done by real experts also not good in that case due probability human errors. The primary goal this project provide best most house investors with help machine learning...

10.1109/icac3n56670.2022.10074128 article EN 2022-12-16

10.14445/23939125/ijems-v5i8p104 article EN cc-by-nc-nd International Journal of Economics and Management Studies 2018-08-25

10.1504/ijcaet.2022.10050427 article EN International Journal of Computer Aided Engineering and Technology 2022-01-01

<p>This letter proposes a novel malicious user prediction model based on quantum machine learning that estimates the vicious entity present in communication system precedently before allocating data distributed environments. The proposed scrutinizes behavior of each and probable breaches using developed predictor unit. computes essential scores associated with request for process unit by generating training samples. exploits computational behavioral properties Qubits Quantum gates...

10.36227/techrxiv.21780695.v1 preprint EN cc-by 2023-01-24

In this paper, we propose SCANING, an unsupervised framework for paraphrasing via controlled noise injection. We focus on the novel task of algebraic word problems having practical applications in online pedagogy as a means to reduce plagiarism well ensure understanding part student instead rote memorization. This is more complex than general-domain corpora due difficulty preserving critical information solution consistency paraphrased problem, managing increased length text and ensuring...

10.48550/arxiv.2302.02780 preprint EN other-oa arXiv (Cornell University) 2023-01-01

Quantum computers are believed to have the ability process huge data sizes which can be seen in machine learning applications. In these applications, general is classical. Therefore, them on a quantum computer, there need for efficient methods used map classical states concise manner. On other hand, verify results of and study algorithms, we able approximate operations into forms that easier simulate with some errors. Motivated by needs, this paper approximation matrices vectors using their...

10.48550/arxiv.2302.04801 preprint EN other-oa arXiv (Cornell University) 2023-01-01
Coming Soon ...