Search Results for author: Ashutosh Kumar

Found 17 papers, 6 papers with code

Dynamics and Computational Principles of Echo State Networks: A Mathematical Perspective

no code implementations16 Apr 2025 Pradeep Singh, Ashutosh Kumar, Sutirtha Ghosh, Hrishit B P, Balasubramanian Raman

Reservoir computing (RC) represents a class of state-space models (SSMs) characterized by a fixed state transition mechanism (the reservoir) and a flexible readout layer that maps from the state space.

State Space Models Time Series Prediction

From Fog to Failure: How Dehazing Can Harm Clear Image Object Detection

no code implementations4 Feb 2025 Ashutosh Kumar, Aman Chadha

This study explores the challenges of integrating human visual cue-based dehazing into object detection, given the selective nature of human perception.

object-detection Object Detection

IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding

no code implementations27 Jan 2025 Sankalp KJ, Ashutosh Kumar, Laxmaan Balaji, Nikunj Kotecha, Vinija Jain, Aman Chadha, Sreyoshi Bhaduri

Known by more than 1. 5 billion people in the Indian subcontinent, Indic languages present unique challenges and opportunities for natural language processing (NLP) research due to their rich cultural heritage, linguistic diversity, and complex structures.

Benchmarking Diversity +2

MoonMetaSync: Lunar Image Registration Analysis

1 code implementation14 Oct 2024 Ashutosh Kumar, Sarthak Kaushal, Shiv Vignesh Murthy

This research contributes to computer vision and planetary science by comparing feature detection methods for lunar imagery and introducing a versatile tool for lunar image registration and evaluation, with implications for multi-resolution image analysis in space exploration applications.

Image Registration

Perceptual Piercing: Human Visual Cue-based Object Detection in Low Visibility Conditions

1 code implementation2 Oct 2024 Ashutosh Kumar

The findings offer a viable solution for enhancing object detection in poor visibility and contribute to the broader understanding of integrating human visual principles into deep learning algorithms for intricate visual recognition challenges.

Autonomous Driving Computational Efficiency +4

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles

1 code implementation18 Jun 2024 Devichand Budagam, Ashutosh Kumar, Mahsa Khoshnoodi, Sankalp KJ, Vinija Jain, Aman Chadha

It assesses the complexity of tasks with the Hierarchical Prompting Index (HPI), which demonstrates the cognitive competencies of LLMs across diverse datasets and offers insights into the cognitive demands that datasets place on different LLMs.

Arithmetic Reasoning Code Generation +10

A Methodology-Oriented Study of Catastrophic Forgetting in Incremental Deep Neural Networks

no code implementations11 May 2024 Ashutosh Kumar, Sonali Agarwal, D Jude Hemanth

In such scenarios, the main concern is catastrophic forgetting(CF), i. e., while learning the sequentially, neural network underfits the old data when it confronted with new data.

Incremental Learning

The Ethics of Interaction: Mitigating Security Threats in LLMs

no code implementations22 Jan 2024 Ashutosh Kumar, Shiv Vignesh Murthy, Sagarika Singh, Swathy Ragupathy

This paper comprehensively explores the ethical challenges arising from security threats to Large Language Models (LLMs).

Chatbot Ethics

Road Rutting Detection using Deep Learning on Images

no code implementations28 Sep 2022 Poonam Kumari Saha, Deeksha Arya, Ashutosh Kumar, Hiroya Maeda, Yoshihide Sekimoto

The proposed road rutting dataset and the results of our research study will help accelerate the research on detection of road rutting using deep learning.

Deep Learning Object +4

Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks

no code implementations Findings (ACL) 2022 Ashutosh Kumar, Aditya Joshi

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models.

Classification

NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

2 code implementations6 Dec 2021 Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann, Aadesh Gupta, Zhenhao Li, Saad Mahamood, Abinaya Mahendiran, Simon Mille, Ashish Shrivastava, Samson Tan, Tongshuang Wu, Jascha Sohl-Dickstein, Jinho D. Choi, Eduard Hovy, Ondrej Dusek, 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, Emile 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 Han, Fabrice Harel-Canada, Antoine Honore, 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 Meoni, Maxime Meyer, Afnan Mir, Nafise Sadat Moosavi, Niklas Muennighoff, Timothy Sum Hon Mun, Kenton Murray, Marcin Namysl, Maria Obedkova, Priti Oli, Nivranshu Pasricha, Jan Pfister, Richard Plant, Vinay Prabhu, Vasile Pais, Libo Qin, Shahab Raji, Pawan Kumar Rajpoot, Vikas Raunak, Roy Rinberg, Nicolas Roberts, Juan Diego Rodriguez, Claude Roux, Vasconcellos P. H. S., Ananya B. Sai, Robin M. Schmidt, Thomas Scialom, Tshephisho Sefara, Saqib N. Shamsi, Xudong Shen, Haoyue Shi, Yiwen Shi, Anna Shvets, Nick Siegel, Damien Sileo, Jamie Simon, Chandan Singh, Roman Sitelew, Priyank Soni, Taylor Sorensen, William Soto, Aman Srivastava, KV Aditya Srivatsa, Tony Sun, Mukund Varma T, A Tabassum, Fiona Anting Tan, Ryan Teehan, Mo Tiwari, Marie Tolkiehn, Athena Wang, Zijian Wang, Gloria Wang, Zijie J. Wang, Fuxuan Wei, Bryan Wilie, Genta Indra Winata, Xinyi Wu, Witold Wydmański, Tianbao Xie, Usama Yaseen, Michael A. Yee, Jing Zhang, Yue Zhang

Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.

Data Augmentation Diversity

Transients generate memory and break hyperbolicity in stochastic enzymatic networks

no code implementations2 Oct 2020 Ashutosh Kumar, R. Adhikari, Arti Dua

We propose new statistical measures, defined in terms of turnover times, to distinguish between the transient and steady states and apply these to experimental data from a landmark experiment that first observed molecular memory in a single enzyme with multiple binding sites.

Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation

1 code implementation NAACL 2019 Ashutosh Kumar, Satwik Bhattamishra, Bh, Manik ari, Partha Talukdar

Inducing diversity in the task of paraphrasing is an important problem in NLP with applications in data augmentation and conversational agents.

Data Augmentation Diversity +2

eCommerceGAN : A Generative Adversarial Network for E-commerce

no code implementations10 Jan 2018 Ashutosh Kumar, Arijit Biswas, Subhajit Sanyal

Exploring the space of all plausible orders could help us better understand the relationships between the various entities in an e-commerce ecosystem, namely the customers and the products they purchase.

Generative Adversarial Network

Cannot find the paper you are looking for? You can Submit a new open access paper.