Publications (88)
Siamese Tracking with Lingual Object Constraints
Maximilian Filtenborg, Efstratios Gavves, Deepak Gupta
Classically, visual object tracking involves following a target object throughout a given video, and it provides us the motion trajectory of the object. However, for many practical…
Empowering Language Model with Guided Knowledge Fusion for Biomedical Document Re-ranking
Deepak Gupta, Dina Demner-Fushman
Pre-trained language models (PLMs) have proven to be effective for document re-ranking task. However, they lack the ability to fully interpret the semantics of biomedical and healt…
One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
Arnav Chavan, Zhuang Liu, Deepak Gupta +2
We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized pro…
BloomNet: A Robust Transformer based model for Bloom's Learning Outcome Classification
Abdul Waheed, Muskan Goyal, Nimisha Mittal +3
Bloom taxonomy is a common paradigm for categorizing educational learning objectives into three learning levels: cognitive, affective, and psychomotor. For the optimization of educ…
Combining Graph-based Dependency Features with Convolutional Neural Network for Answer Triggering
Deepak Gupta, Sarah Kohail, Pushpak Bhattacharyya
Answer triggering is the task of selecting the best-suited answer for a given question from a set of candidate answers if exists. In this paper, we present a hybrid deep learning m…
Parameter Efficient Fine-Tuning for Deep Learning-Based Full-Waveform Inversion
Koustav Ghosal, Abhranta Panigrahi, Arnav Chavan +2
Seismic full waveform inversion (FWI) has seen promising advancements through deep learning. Existing approaches typically focus on task-specific models trained and evaluated in is…
Shall we turn off the media? Global information can destroy local cooperation in the one-dimensional ring
Bilge Aydin, Marta Biondo, Deepak Gupta +7
In this paper we investigate the evolution of cooperation when the interaction structure is strictly local, and hence fitness only depends on local behaviors, while the competition…
Fluctuation theorem for entropy production of a partial system in the weak coupling limit
Deepak Gupta, Sanjib Sabhapandit
Small systems in contact with a heat bath evolve by stochastic dynamics. Here we show that, when one such small system is weakly coupled to another one, it is possible to infer the…
Throughput Performance of 22 Mimo LTE Downlink in a Spatial Correlation Based Microcellular Channel for Wireless Broadband Networks
Sunil Joshi, Deepak Gupta
Multiple Input Multiple Output (MIMO) technology is going to be a viable alternative for future generation wireless broadband services in order to meet the striving requirements fo…
A Dataset for Medical Instructional Video Classification and Question Answering
Deepak Gupta, Kush Attal, Dina Demner-Fushman
This paper introduces a new challenge and datasets to foster research toward designing systems that can understand medical videos and provide visual answers to natural language que…
Entropy production for partially observed harmonic systems
Deepak Gupta, Sanjib Sabhapandit
The probability distribution of the total entropy production in the non-equilibrium steady state follows a symmetry relation called the fluctuation theorem. When a certain part of…
Improving Neural Question Generation using World Knowledge
Deepak Gupta, Kaheer Suleman, Mahmoud Adada +2
In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge h…
Optimal Control of the F-ATPase Molecular Motor
Deepak Gupta, Steven J. Large, Shoichi Toyabe +1
F-ATPase is a rotary molecular motor that \emph{in vivo} is subject to strong nonequilibrium driving forces. There is great interest in understanding the operational principl…
Stochastic efficiency of an isothermal work-to-work converter engine
Deepak Gupta, Sanjib Sabhapandit
We investigate the efficiency of an isothermal Brownian work-to-work converter engine, composed of a Brownian particle coupled to a heat bath at a constant temperature. The system…
DOT-MoE: Differentiable Optimal Transport for MoEfication
Udbhav Bamba, Arnav Chavan, Aryamaan Thakur +2
The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While Mixture of Experts (MoEs) arc…
A Dataset and Benchmark for Consumer Healthcare Question Summarization
Abhishek Basu, Deepak Gupta, Dina Demner-Fushman +1
The quest for seeking health information has swamped the web with consumers health-related questions. Generally, consumers use overly descriptive and peripheral information to expr…
Classifying text using machine learning models and determining conversation drift
Chaitanya Chadha, Vandit Gupta, Deepak Gupta +1
Text classification helps analyse texts for semantic meaning and relevance, by mapping the words against this hierarchy. An analysis of various types of texts is invaluable to unde…
Self-healing Nodes with Adaptive Data-Sharding
Ayush Thakur, Sanskar Chauhan, Ilisha Tomar +2
Data sharding, a technique for partitioning and distributing data among multiple servers or nodes, offers enhancements in the scalability, performance, and fault tolerance of exten…
Hierarchical Deep Multi-modal Network for Medical Visual Question Answering
Deepak Gupta, Swati Suman, Asif Ekbal
Visual Question Answering in Medical domain (VQA-Med) plays an important role in providing medical assistance to the end-users. These users are expected to raise either a straightf…
Wavelet-Accelerated Physics-Informed Quantum Neural Network for Multiscale Partial Differential Equations
Deepak Gupta, Himanshu Pandey, Ratikanta Behera
This work proposes a wavelet-based physics-informed quantum neural network framework to efficiently address multiscale partial differential equations that involve sharp gradients,…
Overview of TREC 2024 Medical Video Question Answering (MedVidQA) Track
Deepak Gupta, Dina Demner-Fushman
One of the key goals of artificial intelligence (AI) is the development of a multimodal system that facilitates communication with the visual world (image and video) using a natura…
Efficient control protocols for an active Ornstein-Uhlenbeck particle
Deepak Gupta, Sabine H. L. Klapp, David A. Sivak
Designing a protocol to efficiently drive a stochastic system is an active field of research. Here we extend such control theory to an active Ornstein-Uhlenbeck particle (AOUP) in…
S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations
Arnav Chavan, Nahush Lele, Udbhav Bamba +3
Activation outliers in large-scale transformer models pose a fundamental challenge to model quantization, creating excessively large ranges that cause severe accuracy drops during…
Resetting with stochastic return through linear confining potential
Deepak Gupta, Arnab Pal, Anupam Kundu
We consider motion of an overdamped Brownian particle subject to stochastic resetting in one dimension. In contrast to the usual setting where the particle is instantaneously reset…
Optimizing Cost through Dynamic Stochastic Resetting
Deepak Gupta, Bart Cleuren
The cost of stochastic resetting is considered within the context of a discrete random walk model. In addition to standard stochastic resetting, for which a reset occurs with a cer…
Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features
Deepak Gupta, Russell Loane, Soumya Gayen +1
Nearest neighbor search (NNS) aims to locate the points in high-dimensional space that is closest to the query point. The brute-force approach for finding the nearest neighbor beco…
Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards
Shweta Yadav, Deepak Gupta, Asma Ben Abacha +1
The growth of online consumer health questions has led to the necessity for reliable and accurate question answering systems. A recent study showed that manual summarization of con…
Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
Ying-Chun Lin, Jennifer Neville, Jack W. Stokes +14
Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems. Users express their sati…
Asymmetric Stochastic Resetting: Modeling Catastrophic Events
Carlos A. Plata, Deepak Gupta, Sandro Azaele
In the classical stochastic resetting problem, a particle, moving according to some stochastic dynamics, undergoes random interruptions that bring it to a selected domain, and then…
NOVO: Unlearning-Compliant Vision Transformers
Soumya Roy, Soumya Banerjee, Vinay Verma +3
Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining da…
Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models
Arnav Chavan, Nahush Lele, Deepak Gupta
Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associa…
A Two-Stage Metaheuristic Algorithm for the Dynamic Vehicle Routing Problem in Industry 4.0 approach
Maryam Abdirad, Krishna Krishnan, Deepak Gupta
Industry 4.0 is a concept that assists companies in developing a modern supply chain (MSC) system when they are faced with a dynamic process. Because Industry 4.0 focuses on mobili…
Quantum Physics-Informed Neural Networks for Solving Integro and Fractional PDEs
Deepak Gupta, Ratikanta Behera
Quantum neural networks have emerged as powerful models for approximating nonlinear functions. Yet their use in solving integro-differential equations (IDEs) and fractional integro…
Inferring entropy production from short experiments
Sreekanth K Manikandan, Deepak Gupta, Supriya Krishnamurthy
We provide a strategy for an exact inference of the average as well as the fluctuations of the entropy production in non-equilibrium systems in the steady state, from the measureme…
Stochastic resetting with refractory periods: pathway formulation and exact results
Gregorio GarcÃa-Valladares, Deepak Gupta, Antonio Prados +1
We look into the problem of stochastic resetting with refractory periods. The model dynamics comprises diffusive and motionless phases. The diffusive phase ends at random time inst…
CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
Abdul Waheed, Muskan Goyal, Deepak Gupta +3
Coronavirus (COVID-19) is a viral disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The spread of COVID-19 seems to have a detrimental effect on the g…
VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
Soumya Banerjee, Vinay K. Verma, Avideep Mukherjee +3
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 li…
Thermodynamic work of partial resetting
Kristian Stølevik Olsen, Deepak Gupta
Partial resetting, whereby a state variable is reset at random times to a value , , generalizes conventional resetting by introducing the resetting…
Bioimpedance a Diagnostic Tool for Tobacco Induced Oral Lesions: a Mixed Model cross-sectional study
Vaibhav Gupta, Poonam Goel, Usha Agrawal +3
Introduction: Electrical impedance spectroscopy (EIS) has recently developed as a novel diagnostic device for screening and evaluating cervical dysplasia, prostate cancer, breast c…
Helping each Other: A Framework for Customer-to-Customer Suggestion Mining using a Semi-supervised Deep Neural Network
Hitesh Golchha, Deepak Gupta, Asif Ekbal +1
Suggestion mining is increasingly becoming an important task along with sentiment analysis. In today's cyberspace world, people not only express their sentiments and dispositions t…
Machine Learning enabled models for YouTube Ranking Mechanism and Views Prediction
Vandit Gupta, Akshit Diwan, Chaitanya Chadha +2
With the continuous increase of internet usage in todays time, everyone is influenced by this source of the power of technology. Due to this, the rise of applications and games Is…
Dynamics of switching processes: general results and applications to intermittent active motion
Ion Santra, Kristian Stølevik Olsen, Deepak Gupta
Systems switching between different dynamical phases is an ubiquitous phenomenon. The general understanding of such a process is limited. To this end, we present a general expressi…
Partial entropy production in heat transport
Deepak Gupta, Sanjib Sabhapandit
We consider a system of two Brownian particles (say A and B), coupled to each other via harmonic potential of stiffness constant . Particle-A is connected to two heat baths of c…
Auto Analysis of Customer Feedback using CNN and GRU Network
Deepak Gupta, Pabitra Lenka, Harsimran Bedi +2
Analyzing customer feedback is the best way to channelize the data into new marketing strategies that benefit entrepreneurs as well as customers. Therefore an automated system whic…
Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward
Arnav Chavan, Raghav Magazine, Shubham Kushwaha +2
Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancement…
Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches
Deepak Gupta, Kush Attal, Dina Demner-Fushman
The increase in the availability of online videos has transformed the way we access information and knowledge. A growing number of individuals now prefer instructional videos as th…
Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts
Rohit Agarwal, Deepak Gupta, Alexander Horsch +1
Many real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the a…
Thermodynamic uncertainty relations in a linear system
Deepak Gupta, Amos Maritan
We consider a Brownian particle in harmonic confinement of stiffness , in one dimension in the underdamped regime. The whole setup is immersed in a heat bath at temperature .…
Reinforced Multi-task Approach for Multi-hop Question Generation
Deepak Gupta, Hardik Chauhan, Akella Ravi Tej +2
Question generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer. While sequence t…
Inference of a time delay in stochastic systems
Robin A. Kopp, Sabine H. L. Klapp, Deepak Gupta
Time delay is ubiquitous in many experimental and real-world situations. It is often unclear whether time delay plays a significant role in observed phenomena, and if it does, how…
SMPOST: Parts of Speech Tagger for Code-Mixed Indic Social Media Text
Deepak Gupta, Shubham Tripathi, Asif Ekbal +1
Use of social media has grown dramatically during the last few years. Users follow informal languages in communicating through social media. The language of communication is often…
Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learning
Soumya Roy, Vinay K Verma, Deepak Gupta
This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are effic…
CHQ-Summ: A Dataset for Consumer Healthcare Question Summarization
Shweta Yadav, Deepak Gupta, Dina Demner-Fushman
The quest for seeking health information has swamped the web with consumers' health-related questions. Generally, consumers use overly descriptive and peripheral information to exp…
Stochastic resetting with stochastic returns using external trap
Deepak Gupta, Carlos A Plata, Anupam Kundu +1
In the past few years, stochastic resetting has become a subject of immense interest. Most of the theoretical studies so far focused on instantaneous resetting which is, however, a…
Tighter thermodynamic bound on speed limit in systems with unidirectional transitions
Deepak Gupta, Daniel M. Busiello
We consider a general discrete state-space system with both unidirectional and bidirectional links. In contrast to bidirectional links, there is no reverse transition along the uni…
Fluctuations of entropy production of a run-and-tumble particle
Prajwal Padmanabha, Daniel Maria Busiello, Amos Maritan +1
Out-of-equilibrium systems continuously generate entropy, with its rate of production being a fingerprint of non-equilibrium conditions. In small-scale dissipative systems subject…
Ginzburg-Landau amplitude equation for nonlinear nonlocal models
Stefano Garlaschi, Deepak Gupta, Amos Maritan +1
Regular spatial structures emerge in a wide range of different dynamics characterized by local and/or nonlocal coupling terms. In several research fields this has spurred the study…
Work fluctuations and Jarzynski equality in stochastic resetting
Deepak Gupta, Carlos A. Plata, Arnab Pal
We consider the paradigm of an overdamped Brownian particle in a potential well, which is modulated through an external protocol, in the presence of stochastic resetting. Thus, in…
Thermodynamic cost of finite-time stochastic resetting
Kristian Stølevik Olsen, Deepak Gupta, Francesco Mori +1
Recent experiments have implemented resetting by means of an external trap, whereby a system relaxes to the minimum of the trap and is reset in a finite time. In this work, we set…
Hiding Data in Images Using Cryptography and Deep Neural Network
Kartik Sharma, Ashutosh Aggarwal, Tanay Singhania +2
Steganography is an art of obscuring data inside another quotidian file of similar or varying types. Hiding data has always been of significant importance to digital forensics. Pre…
Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures
Akash Guna R. T, Arnav Chavan, Deepak Gupta
Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling…
Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy
Deepak Gupta, Rajkumar Pujari, Asif Ekbal +4
In this paper, we propose a hybrid technique for semantic question matching. It uses our proposed two-layered taxonomy for English questions by augmenting state-of-the-art deep lea…
Emergence of ecological structure and species rarity from fluctuating metabolic strategies
Davide Zanchetta, Deepak Gupta, Sofia Moschin +3
Ecosystems frequently display the coexistence of diverse species under resource competition, typically resulting in skewed distributions of rarity and abundance. A potential driver…
Exact distribution for work and stochastic efficiency of an isothermal machine
Deepak Gupta
We consider an isothermal machine composed of two Brownian particles (say particle A and B) connected by a harmonic spring. A constant load is attached to particle A, and the parti…
Question-aware Transformer Models for Consumer Health Question Summarization
Shweta Yadav, Deepak Gupta, Asma Ben Abacha +1
Searching for health information online is becoming customary for more and more consumers every day, which makes the need for efficient and reliable question answering systems more…
Overview of TREC 2024 Biomedical Generative Retrieval (BioGen) Track
Deepak Gupta, Dina Demner-Fushman, William Hersh +2
With the advancement of large language models (LLMs), the biomedical domain has seen significant progress and improvement in multiple tasks such as biomedical question answering, l…
Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation
Humair Raj Khan, Deepak Gupta, Asif Ekbal
Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering m…
Efficiently driving F molecular motor in experiment by suppressing nonequilibrium variation
Takahide Mishima, Deepak Gupta, Yohei Nakayama +4
F-ATPase (F) is central to cellular energy transduction. Forcibly rotated by another motor F, F catalyzes ATP synthesis by converting mechanical work into…
Learning to Answer Multilingual and Code-Mixed Questions
Deepak Gupta
Question-answering (QA) that comes naturally to humans is a critical component in seamless human-computer interaction. It has emerged as one of the most convenient and natural meth…
Enhancing Deep Learning based RMT Data Inversion using Gaussian Random Field
Koustav Ghosal, Arun Singh, Samir Malakar +2
Deep learning (DL) methods have emerged as a powerful tool for the inversion of geophysical data. When applied to field data, these models often struggle without additional fine-tu…
Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes
Anant Khandelwal, Happy Mittal, Shreyas Sunil Kulkarni +1
E-commerce websites (e.g. Amazon) have a plethora of structured and unstructured information (text and images) present on the product pages. Sellers often either don't label or mis…
Coarse-grained entropy production with multiple reservoirs: unraveling the role of time-scales and detailed balance in biology-inspired systems
Daniel M. Busiello, Deepak Gupta, Amos Maritan
A general framework to describe a vast majority of biology-inspired systems is to model them as stochastic processes in which multiple couplings are in play at the same time. Molec…
A Three-Stage Algorithm for the Large Scale Dynamic Vehicle Routing Problem with an Industry 4.0 Approach
Maryam Abdirad, Krishna Krishnan, Deepak Gupta
Companies are eager to have a smart supply chain especially when they have a dynamic system. Industry 4.0 is a concept which concentrates on mobility and real-time integration. Thu…
Rescaling CNN through Learnable Repetition of Network Parameters
Arnav Chavan, Udbhav Bamba, Rishabh Tiwari +1
Deeper and wider CNNs are known to provide improved performance for deep learning tasks. However, most such networks have poor performance gain per parameter increase. In this pape…
Entropy Production Rate in Stochastically Time-evolving Asymmetric Networks
Tuan Pham, Deepak Gupta
Fluctuations in parameters that are typically treated as fixed play a crucial role in the behavior of complex systems. However, to date, we lack a general non-equilibrium thermodyn…
Inducing and optimizing Markovian Mpemba effect with stochastic reset
Daniel Maria Busiello, Deepak Gupta, Amos Maritan
A hot Markovian system can cool down faster than a colder one: this is known as the Mpemba effect. Here, we show that a non-equilibrium driving via stochastic reset can induce this…
Domain Controlled Title Generation with Human Evaluation
Abdul Waheed, Muskan Goyal, Nimisha Mittal +1
We study automatic title generation and present a method for generating domain-controlled titles for scientific articles. A good title allows you to get the attention that your res…
BioACE: An Automated Framework for Biomedical Answer and Citation Evaluations
Deepak Gupta, Davis Bartels, Dina Demner-Fushman
With the increasing use of large language models (LLMs) for generating answers to biomedical questions, it is crucial to evaluate the quality of the generated answers and the refer…
Nonequilibrium fluctuations in a harmonic trap with annealed stochastic stiffness
Deepak Gupta, Sabine H. L. Klapp
We provide a comprehensive analysis of the positional dynamics and average thermodynamics of an overdamped Brownian particle subject to both, harmonic confinement and annealed diso…
Diagnosis of Breast Cancer Based on Modern Mammography using Hybrid Transfer Learning
Aditya Khamparia, Subrato Bharati, Prajoy Podder +4
Breast cancer is a common cancer for women. Early detection of breast cancer can considerably increase the survival rate of women. This paper mainly focuses on transfer learning pr…
Work fluctuations for diffusion dynamics submitted to stochastic return
Deepak Gupta, Carlos A. Plata
Returning a system to a desired state under a force field involves a thermodynamic cost, i.e., {\it work}. This cost fluctuates for a small-scale system from one experimental reali…
Heat fluctuations in a harmonic chain of active particles
Deepak Gupta, David A. Sivak
One of the major challenges in stochastic thermodynamics is to compute the distributions of stochastic observables for small-scale systems for which fluctuations play a significant…
Overview of TREC 2025 Biomedical Generative Retrieval (BioGen) Track
Deepak Gupta, Dina Demner-Fushman, William Hersh +2
Recent advances in large language models (LLMs) have made significant progress across multiple biomedical tasks, including biomedical question answering, lay-language summarization…
Stochastic resetting in underdamped Brownian motion
Deepak Gupta
We consider a single Brownian particle in one dimension in a medium at a constant temperature in the underdamped regime. We stochastically reset the position of the Brownian partic…
Surgical Feature-Space Decomposition of LLMs: Why, When and How?
Arnav Chavan, Nahush Lele, Deepak Gupta
Low-rank approximations, of the weight and feature space can enhance the performance of deep learning models, whether in terms of improving generalization or reducing the latency o…
Thermodynamic Cost of Recurrent Erasure
Deepak Gupta, Kristian Stølevik Olsen, Supriya Krishnamurthy
Recent experiments have implemented resetting by means of a time-varying external harmonic trap whereby the trap stiffness is changed from an initial to a final value in finite-tim…
MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering
Vinay Kumar Verma, Shreyas Sunil Kulkarni, Happy Mittal +1
Question Answering (QA) and Visual Question Answering (VQA) are well-studied problems in the language and vision domain. One challenging scenario involves multiple sources of infor…
Effective Resource-Competition Model for Species Coexistence
Deepak Gupta, Stefano Garlaschi, Samir Suweis +2
Local coexistence of species in large ecosystems is traditionally explained within the broad framework of niche theory. However, its rationale hardly justifies rich biodiversity ob…