papers

Publications (105)

cs.CV2024

Frozen Feature Augmentation for Few-Shot Image Classification

Andreas Bär, Neil Houlsby, Mostafa Dehghani +1

Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream…

cs.CV2023

Image Captioners Are Scalable Vision Learners Too

Michael Tschannen, Manoj Kumar, Andreas Steiner +3

Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large mult…

cond-mat.dis-nn2020

On the comparison of optimization algorithms for the random-field Potts model

Manoj Kumar, Martin Weigel

For many systems with quenched disorder the study of ground states can crucially contribute to a thorough understanding of the physics at play, be it for the critical behavior if t…

cond-mat.stat-mech2017

Ordering Kinetics in the Random Bond XY Model

Manoj Kumar, Swarnajit Chatterjee, Raja Paul +1

We present a comprehensive Monte Carlo study of domain growth in the random-bond XY model with non-conserved kinetics. The presence of quenched disorder slows down domain growth in…

hep-ph2025

Predictive one-zero with vanishing sub-trace texture in neutrino mass matrix in light of dark matter and neutrinoless double beta decay

Ankush, Sangeeta Dey, Rishu Verma +3

In this work, we investigate a predictive class of neutrino mass matrices characterized by one texture zero and one vanishing sub-trace within the framework of the scotogenic model…

cs.OH2013

Services in Android can Share Your Personal Information in Background

Manoj Kumar, Sheshendra Rathi

Mobile phones have traveled a very long journey in a very short span of time since its inception in 1973.This wonderful toy of 20th century has started playing significant role in…

cond-mat.stat-mech2022

Critical behavior of the three-state random-field Potts model in three dimensions

Manoj Kumar, Varsha Banerjee, Sanjay Puri +1

Enormous advances have been made in the past 20 years in our understanding of the random-field Ising model, and there is now consensus on many aspects of its behavior at least in t…

cs.CL2018

Measuring Conversational Productivity in Child Forensic Interviews

Victor Ardulov, Manoj Kumar, Shanna Williams +2

Child Forensic Interviewing (FI) presents a challenge for effective information retrieval and decision making. The high stakes associated with the process demand that expert legal…

cs.CV2020

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

Manoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan +4

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a…

eess.AS2019

Speaker diarization using latent space clustering in generative adversarial network

Monisankha Pal, Manoj Kumar, Raghuveer Peri +5

In this work, we propose deep latent space clustering for speaker diarization using generative adversarial network (GAN) backprojection with the help of an encoder network. The pro…

cs.CR2005

Faults and Improvements of an Enhanced Remote User Authentication Scheme Using Smart Cards

Manoj Kumar

In 2000, Hwang and Li proposed a remote user authentication scheme using smart cards to solve the problems of Lamport scheme. Later, Chan- Chang, Shen- Lin- Hwang and then Chang-Hw…

cs.CR2004

Some Applications of Directed Signature Scheme

Sunder Lal, Manoj Kumar

Directed signature scheme is applicable when the signed message contains information sensitive to the receiver, because only receiver can directly verify the signature and that he/…

physics.plasm-ph2025

Identification and Characterization of a New Disruption Regime in ADITYA-U Tokamak

Soumitra Banerjee, Harshita Raj, Sk Injamul Hoque +22

Disruptions continue to pose a significant challenge to the stable operation and future design of tokamak reactors. A comprehensive statistical investigation carried out on the ADI…

cs.CV2024

XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration

Denys Rozumnyi, Nadine Bertsch, Othman Sbai +6

Tracking the full body motions of users in XR (AR/VR) devices is a fundamental challenge to bring a sense of authentic social presence. Due to the absence of dedicated leg sensors,…

cs.CV2023

Scaling Vision Transformers to 22 Billion Parameters

Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…

physics.plasm-ph2022

Intense multicycle THz pulses generated by laser-produced nanoplasmas

Manoj Kumar, Hyung Seon Song, Jaeho Lee +3

We present a novel scheme to obtain robust, narrowband, and tunable THz emission by using a nano-dimensional overdense plasma target that is irradiated by two counter-propagating d…

eess.AS2020

Designing Neural Speaker Embeddings with Meta Learning

Manoj Kumar, Tae Jin-Park, Somer Bishop +1

Neural speaker embeddings trained using classification objectives have demonstrated state-of-the-art performance in multiple applications. Typically, such embeddings are trained on…

cond-mat.stat-mech2021

Domain Growth and Aging in the Random Field XY Model: A Monte Carlo Study

Ramgopal Agrawal, Manoj Kumar, Sanjay Puri

We use large-scale Monte Carlo simulations to obtain comprehensive results for domain growth and aging in the random field XY model in dimensions . After a deep quench from…

cond-mat.mtrl-sci2016

Determination of Surface Morphology of TiO2 nanostructure using synchrotron X-ray standing wave technique

Gangadhar Das, Manoj Kumar, A. K. Biswas +3

Nanostructures of Titanium oxide (TiO2) are being studied for many promising applications, e.g., solar photovoltaics, solar water splitting for H2 fuel generation etc., due to thei…

cs.CR2005

Directed Threshold Multi – Signature Scheme without SDC

Manoj Kumar

In this paper, we propose a Directed threshold multisignature scheme without SDC. This signature scheme is applicable when the message is sensitive to the signature receiver; and t…

cond-mat.dis-nn2018

Approximate ground states of the random-field Potts model from graph cuts

Manoj Kumar, Ravinder Kumar, Martin Weigel +3

While the ground-state problem for the random-field Ising model is polynomial, and can be solved using a number of well-known algorithms for maximum flow or graph cut, the analogue…

math.AP2018

Exact solutions of fractional partial differential equations by Sumudu transform iterative method

Manoj Kumar, Varsha Daftardar-Gejji

Developing analytical methods for solving fractional partial differential equations (FPDEs) is an active area of research. Especially finding exact solutions of FPDEs is a challeng…

cs.CV2021

Colorization Transformer

Manoj Kumar, Dirk Weissenborn, Nal Kalchbrenner

We present the Colorization Transformer, a novel approach for diverse high fidelity image colorization based on self-attention. Given a grayscale image, the colorization proceeds i…

cs.CR2005

The Modified Scheme is still vulnerable to the parallel Session Attack

Manoj Kumar

In 2002, Chien–Jan–Tseng introduced an efficient remote user authentication scheme using smart cards. Further, in 2004, W. C. Ku and S. M. Chen proposed an efficient re…

physics.optics2017

Incoherent digital holograms acquired by interferenceless coded aperture correlation holography system without refractive lenses

Manoj Kumar, A. Vijayakumar, Joseph Rosen

We present a lensless, interferenceless incoherent digital holography technique based on the principle of coded aperture correlation holography. The acquired digital hologram by th…

math.NT2017

The Signs in Elliptic Nets

Amir Akbary, Manoj Kumar, Soroosh Yazdani

We give a generalization of a theorem of Silverman and Stephens regarding the signs in an elliptic divisibility sequence to the case of an elliptic net. We also describe applicatio…

cs.LG2024

Modularity aided consistent attributed graph clustering via coarsening

Samarth Bhatia, Yukti Makhija, Manoj Kumar +1

Graph clustering is an important unsupervised learning technique for partitioning graphs with attributes and detecting communities. However, current methods struggle to accurately…

cond-mat.soft2024

Rigid flocks, undulatory gaits, and chiral foldamers in a chemically active polymer

Arvin Gopal Subramaniam, Manoj Kumar, Shashi Thutupalli +1

Active matter systems - such as a collection of active colloidal particles - operate far from equilibrium with complex inter-particle interactions that govern their collective dyna…

cs.CY2011

Impact of the Evolution of Smart Phones in Education Technology and its Application in Technical and Professional Studies: Indian Perspective

Manoj Kumar

The greatness of any nation depends largely on the system of education that is used to nurture its talent from within. With the digital era taking the spotlight, and the world rapi…

math.FA2019

Optimal extension of the Fourier transform and convolution operator on compact groups

Manoj Kumar, N. Shravan Kumar

Let be a compact group (not necessarily abelian) and let be a Young function satisfying the -condition. We determine the optimal domain and the associated extended o…

cs.OH2010

Level Shifter Design for Low Power Applications

Manoj Kumar, Sandeep K. Arya, Sujata Pandey

With scaling of Vt sub-threshold leakage power is increasing and expected to become significant part of total power consumption In present work three new configurations of level sh…

hep-ph2022

Minimizing the phase structure of quark mass matrices

Nikhila Awasthi, Manoj Kumar, Monika Randhawa +1

Fritzsch-Xing matrices are a particular class of texture 4 zero hermitian quark mass matrices, known to be successful in accommodating the quark mixing data. In the present work, i…

cs.CL2021

ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification

Manoj Kumar, Varun Kumar, Hadrien Glaude +3

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this pro…

math.GR2004

Class-Preserving Automorphisms of a Family of Finite p-Groups

Manoj Kumar

I withdraw my paper from arXiv because there is a technical error in the proof of Theorem 1.1. And because of this error, all the results in the paper are untrue. I am very sorry f…

cs.CL2023

Large language models can segment narrative events similarly to humans

Sebastian Michelmann, Manoj Kumar, Kenneth A. Norman +1

Humans perceive discrete events such as "restaurant visits" and "train rides" in their continuous experience. One important prerequisite for studying human event perception is the…

cond-mat.stat-mech2019

Effects of Frustration on Fluctuation-dissipation Relations

Federico Corberi, Manoj Kumar, Eugenio Lippiello +1

We study numerically the aging properties of the two-dimensional Ising model with quenched disorder considered in our recent paper [Phys. Rev. E 95, 062136 (2017)], where frustrati…

cond-mat.soft2025

Temperature switchable self-propulsion activity of liquid crystalline microdroplets

Manoj Kumar, Siddharth Sane, Aniruddh Murali +1

We report on a switchable emulsion droplet microswimmer by utilizing a temperature-dependent transition of the droplet phase. The droplets, made from a liquid crystalline (LC) smec…

cs.CR2004

A Directed -Threshold Multi-Signature Scheme

Sunder lal, Manoj Kumar

In this paper, we propose a Directed Threshold Multi-Signature Scheme. In this threshold signature scheme, any malicious set of signers cannot impersonate any other set of signers…

cs.LG2021

Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks

Lasse Espeholt, Shreya Agrawal, Casper Sønderby +7

The problem of forecasting weather has been scientifically studied for centuries due to its high impact on human lives, transportation, food production and energy management, among…

cs.CC2021

Necessary and Sufficient Condition for Satisfiability of a Boolean Formula in CNF and its Implications on P versus NP problem

Manoj Kumar

Boolean satisfiability problem has applications in various fields. An efficient algorithm to solve satisfiability problem can be used to solve many other problems efficiently. The…

q-bio.PE2020

Age structured SIR model for the spread of infectious diseases through indirect contacts

Manoj Kumar, Syed Abbas

In this article, we discuss an age-structured SIR model in which disease not only spread through direct person to person contacts for e.g. infection due to surface contamination bu…

cs.CR2004

A Directed Signature Scheme and its Applications

Sunder Lal, Manoj Kumar

This paper presents a directed signature scheme with the property that the signature can be verified only with the help of signer or signature receiver. We also propose its applica…

cs.CR2005

An Improved Remote User Authentication Scheme Using Smart Cards

Manoj Kumar

In 2000, Hwang and Li proposed a new remote user authentication scheme using smart cards. In the same year, Chan and Cheng pointed out that Hwang and Li’s scheme is not secur…

eess.AS2020

Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap

Tae Jin Park, Kyu J. Han, Manoj Kumar +1

In this study, we propose a new spectral clustering framework that can auto-tune the parameters of the clustering algorithm in the context of speaker diarization. The proposed fram…

cs.AI2022

Functional Optimization Reinforcement Learning for Real-Time Bidding

Yining Lu, Changjie Lu, Naina Bandyopadhyay +2

Real-time bidding is the new paradigm of programmatic advertising. An advertiser wants to make the intelligent choice of utilizing a \textbf{Demand-Side Platform} to improve the pe…

eess.AS2019

A study of semi-supervised speaker diarization system using gan mixture model

Monisankha Pal, Manoj Kumar, Raghuveer Peri +1

We propose a new speaker diarization system based on a recently introduced unsupervised clustering technique namely, generative adversarial network mixture model (GANMM). The propo…

math.FA2023

Pego theorem on compact groups

Manoj Kumar

The Pego theorem characterizes the precompact subsets of the square-integrable functions on via the Fourier transform. We prove the analogue of the Pego theorem on c…

cs.CY2013

The Wonderful Toy of 20th Century can be a Disaster in 21st Century:Scenario and Policies Regarding Mobile Waste in India

Neeta Sharma, Manoj Kumar

The subscribers base of mobile phones is increasing globally with a rapid rate.The sale of mobile phones has exceeded those of personal computers.India is the second largest teleco…

cs.DB2021

KEA: Tuning an Exabyte-Scale Data Infrastructure

Yiwen Zhu, Subru Krishnan, Konstantinos Karanasos +12

Microsoft's internal big-data infrastructure is one of the largest in the world -- with over 300k machines running billions of tasks from over 0.6M daily jobs. Operating this infra…

cs.CR2021

Encrypted Data Processing

Jessica Tseng, Gianfranco Bilardi, Kattamuri Ekanadham +3

In this paper, we present a comprehensive architecture for confidential computing, which we show to be general purpose and quite efficient. It executes the application as is, witho…

eess.AS2019

Learning Domain Invariant Representations for Child-Adult Classification from Speech

Rimita Lahiri, Manoj Kumar, Somer Bishop +1

Diagnostic procedures for ASD (autism spectrum disorder) involve semi-naturalistic interactions between the child and a clinician. Computational methods to analyze these sessions r…

eess.AS2020

Meta-learning with Latent Space Clustering in Generative Adversarial Network for Speaker Diarization

Monisankha Pal, Manoj Kumar, Raghuveer Peri +5

The performance of most speaker diarization systems with x-vector embeddings is both vulnerable to noisy environments and lacks domain robustness. Earlier work on speaker diarizati…

cs.CR2004

A Directed Threshold - Signature Scheme

Sunder Lal, Manoj Kumar

Directed signature is the solution of such problems when the signed message contains information sensitive to the signature receiver. Generally, in many application of directed sig…

cs.CR2004

A Digital Signature with Threshold Generation and Verification

Sunder lal, Manoj Kumar

This paper proposes a signature scheme where the signatures are generated by the cooperation of a number of people from a given group of senders and the signatures are verified by…

cs.AI2025

Certifying Counterfactual Bias in LLMs

Isha Chaudhary, Qian Hu, Manoj Kumar +3

Large Language Models (LLMs) can produce biased responses that can cause representational harms. However, conventional studies are insufficient to thoroughly evaluate biases across…

cond-mat.soft2024

Emergent dynamics due to chemo-hydrodynamic self-interactions in active polymers

Manoj Kumar, Aniruddh Murali, Arvin Gopal Subramaniam +2

The field of synthetic active matter has, thus far, been led by efforts to create point-like, isolated (yet interacting) self-propelled objects (\emph{e.g.} colloids, droplets, mic…

physics.plasm-ph2024

Narrowband THz Emission from a Plasma Oscillator Imbedded in a Plasma Density Gradient

Manoj Kumar, Bernhard Ersfeld, Jaeho Lee +8

A novel method is presented for generating radiation using the beat wave associated with a bi-frequency laser pulse, to excite plasma oscillations in a plasma slab with a density g…

cs.LG2026

QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding

Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya +3

Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work reduces this footprint by evi…

q-bio.PE2024

Analysis of a mathematical model for malaria using data-driven approach

Adithya Rajnarayanan, Manoj Kumar, Abdessamad Tridane

Malaria is one of the deadliest diseases in the world, every year millions of people become victims of this disease and many even lose their lives. Medical professionals and the go…

cs.CV2024

PaliGemma: A versatile 3B VLM for transfer

Lucas Beyer, Andreas Steiner, André Susano Pinto +32

PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly know…

cond-mat.dis-nn2022

Quasi-exact ground-state algorithm for the random-field Potts model

Manoj Kumar, Martin Weigel

The use of combinatorial optimization algorithms has contributed substantially to the major progress that has occurred in recent years in the understanding of the physics of disord…

cond-mat.mtrl-sci2025

Investigation on Structural, Optical, Thermal, and Magnetic Properties of Bismuth Ferrite Nanoparticles Synthesized at Lower Annealing Temperature

Naresh Prajapati, G. Surya Prakash, Manoj Kumar +1

Due to its multiferroic properties and narrow optical bandgap, Bismuth ferrite has been widely explored for spintronics, photovoltaics, and photocatalysis applications. Bismuth fer…

cond-mat.mes-hall2019

Graphene Quantum Dot as a Probe for DNA Nucleobase Detection: A First Principle Study

Manoj Kumar, Neetika Thakur, Munish Sharma

In this study, structural stability, electronic, optical and vibrational properties of DNA nucleobase adsorbed Graphene Quantum Dot (GQD) has been investigated using density functi…

stat.AP2012

On the proficient use of GEV distribution: a case study of subtropical monsoon region in India

Ripunjai K. Shukla, M. Trivedi, Manoj Kumar

The paper deals with the probabilistic estimates of extreme maximum rainfall (Annual basis) in the Ranchi, Jharkhand (India). Extreme Value Distribution family models are tried to…

cond-mat.mes-hall2009

Defect free visible photoluminescence from laser-generated germanium nanoparticles

Manoj Kumar, Rajesh Kumar, Vivek Kumar +1

Origin of room temperature visible photoluminescence (PL) from defect free germanium (Ge) nanoparticles have been discussed here. The Ge nanoparticles produced by laser-induced etc…

cs.AR2016

Design and Implementation of an Improved Carry Increment Adder

Aribam Balarampyari Devi, Manoj Kumar, Romesh Laishram

A complex digital circuit comprises of adder as a basic unit. The performance of the circuit depends on the design of this basic adder unit. The speed of operation of a circuit is…

stat.ML2022

A Unified Framework for Optimization-Based Graph Coarsening

Manoj Kumar, Anurag Sharma, Sandeep Kumar

Graph coarsening is a widely used dimensionality reduction technique for approaching large-scale graph machine learning problems. Given a large graph, graph coarsening aims to lear…

math.AP2020

Analysis of steady state solutions to an age structured SEQIR model with optimal vaccination

Manoj Kumar, Syed Abbas

Quarantine of those individuals who are suspected of being infected is one of the intervention measures to contain the spread of an infectious disease. We propose an age structured…

cs.CR2004

The Password Change Phase is Still Insecure

Manoj Kumar

In 2004, W. C. Ku and S. M. Chen proposed an efficient remote user authentication scheme using smart cards to solve the security problems of Chien et al.'s scheme. Recently, Hsu an…

cond-mat.stat-mech2020

Growth Kinetics and Aging Phenomena in a Frustrated System

Manoj Kumar, Federico Corberi, Eugenio Lippiello +1

We study numerically the ordering kinetics in a two-dimensional Ising model with random coupling where the fraction of antiferromagnetic links can be gradually tuned. We show t…

math.FA2019

Fourier analysis associated to a vector measure on a compact group

Manoj Kumar, N. Shravan Kumar

In this paper, we introduce and study the Fourier transform of functions which are integrable with respect to a vector measure on a compact group (not necessarily abelian). We also…

q-fin.GN2026

Prediction of bank transaction fraud using TabNet an adaptive deep learning architecture

Prashanth BS, Manoj Kumar, Ariful Hoque +4

The development of online banking has brought about an increase in fraudulent operations, which is a major problem for banks. This study delves into the urgent requirement for inte…

cond-mat.stat-mech2025

Ultraslow Growth of Domains in a Random-Field System With Correlated Disorder

Subhanker Howlader, Prasenjit Das, Manoj Kumar

We study domain growth kinetics in a random-field system in the presence of a spatially correlated disorder after an instantaneous quench at a finite temperature $T…

cond-mat.stat-mech2017

Equilibrium structure and off-equilibrium kinetics of a magnet with tunable frustration

Federico Corberi, Manoj Kumar, Eugenio Lippiello +1

We study numerically a two-dimensional random-bond Ising model where frustration can be tuned by varying the fraction of antiferromagnetic coupling constants. At low temperatur…

cond-mat.stat-mech2023

Domain statistics in the relaxation of the one-dimensional Ising model with strong long-range interactions

Federico Corberi, Manoj Kumar, Eugenio Lippiello +1

After a zero temperature quench, we study the kinetics of the one-dimensional Ising model with long-range interactions between spins at distance decaying as , with $α…

cond-mat.stat-mech2020

Transport, correlations, and chaos in a classical disordered anharmonic chain

Manoj Kumar, Anupam Kundu, Manas Kulkarni +2

We explore transport properties in a disordered nonlinear chain of classical harmonic oscillators and thereby identify a regime exhibiting behavior analogous to that seen in quantu…

math.FA2022

Titchmarsh theorems on Damek-Ricci spaces via moduli of continuity of higher order

Manoj Kumar, Vishvesh Kumar, Michael Ruzhansky

A classical theorem of Titchmarsh relates the -Lipschitz functions and decay of the Fourier transform of the functions. In this note, we prove the Titchmarsh theorem for Damek…

cs.MS2016

Mathematical Foundations of the GraphBLAS

Jeremy Kepner, Peter Aaltonen, David Bader +13

The GraphBLAS standard (GraphBlas.org) is being developed to bring the potential of matrix based graph algorithms to the broadest possible audience. Mathematically the Graph- BLAS…

eess.SY2026

A Survey of Smart Grid Emerging Use Cases and Relevant 5G and 6G Capabilities and Features

Manoj Kumar, Nishith D. Tripathi, Jeffrey H. Reed

The growing complexity of modern energy systems has led to the adoption of Smart Grid (SG) that use advanced communication technologies to facilitate efficient, reliable, secure, a…

cs.NI2013

Multi Constraint Satisfying AODV routing using Fuzzy Logic

Gurpreet Singh Saini, Manoj Kumar

Mobile Networks are in need of what we call as an e-age. There have been numerous advancements in this field and soft computing has gained roots in this Mobile Ad-hoc Network domai…

cs.NI2010

Coverage and Connectivity Aware Neural Network Based Energy Efficient Routing in Wireless Sensor Networks

Neeraj Kumar, Manoj Kumar, R. B. Patel

There are many challenges when designing and deploying wireless sensor networks (WSNs). One of the key challenges is how to make full use of the limited energy to prolong the lifet…

cs.DC2024

Towards Building Autonomous Data Services on Azure

Yiwen Zhu, Yuanyuan Tian, Joyce Cahoon +35

Modern cloud has turned data services into easily accessible commodities. With just a few clicks, users are now able to access a catalog of data processing systems for a wide range…

cs.OH2012

Single bit full adder design using 8 transistors with novel 3 transistors XNOR gate

Manoj Kumar, Sandeep K. Arya, Sujata Pandey

In present work a new XNOR gate using three transistors has been presented, which shows power dissipation of 550.7272W in 0.35m technology with supply voltage of 3.3V. Mini…

cs.CV2018

Parallel Architecture and Hyperparameter Search via Successive Halving and Classification

Manoj Kumar, George E. Dahl, Vijay Vasudevan +1

We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in stages of parallel…

cond-mat.stat-mech2025

Ordering transition of the three-dimensional four-state random-field Potts model

Manoj Kumar, Martin Weigel

Spin systems exposed to the influence of random magnetic fields are paradigmatic examples for studying the effect of quenched disorder on condensed-matter systems. In this context,…

cs.CV2023

Dual PatchNorm

Manoj Kumar, Mostafa Dehghani, Neil Houlsby

We propose Dual PatchNorm: two Layer Normalization layers (LayerNorms), before and after the patch embedding layer in Vision Transformers. We demonstrate that Dual PatchNorm outper…

cond-mat.mtrl-sci2025

White LED-based photocatalytic treatment using recoverable cobalt ferrite nanoparticles

Naresh Prajapati, Manoj Kumar, Vidit Pandey +2

Contamination of freshwater sources has been alarming due to the widespread use of toxic chemicals in various industries. Advanced oxidation processes (AOPs) such as photocatalysis…

cond-mat.supr-con2021

Superconducting Properties of LaSrCuO-SrIrO multilayers

Himanshu Pandey, Manoj Kumar, D. Tripathi +1

We study superconducting properties in multilayer thin films consisting of superconducting LaSrCuO (LSCO) and Mott insulator SrIrO (SIO) and report en…

math.FA2019

Convolution structures for an Orlicz space with respect to vector measures on a compact group

Manoj Kumar, N. Shravan Kumar

The aim of this paper is to present some results about the space L^Φ(ν), where νis a vector measure on a compact (not necessarily abelian) group and Φis a Young function. We sh…

hep-ph2025

Minimal structure for neutrino mass matrix

Manoj Kumar, Nikhila Awasthi, Monika Randhawa +1

Taking clue from the minimal structure of texture 4-zero hermitian mass matrices, which are very successful in accommodating quark mixing data, we propose a form of texture 2-zero…

cond-mat.stat-mech2021

Coexistence of coarsening and mean field relaxation in the long-range Ising chain

Federico Corberi, Alessandro Iannone, Manoj Kumar +2

We study the kinetics after a low temperature quench of the one-dimensional Ising model with long range interactions between spins at distance decaying as . For

eess.AS2019

Meta-learning for robust child-adult classification from speech

Nithin Rao Koluguri, Manoj Kumar, So Hyun Kim +2

Computational modeling of naturalistic conversations in clinical applications has seen growing interest in the past decade. An important use-case involves child-adult interactions…

cond-mat.mes-hall2014

Domain wall motions in perpendicularly magnetized CoFe/Pd multilayer nanowire

Zhaoliang Meng, Manoj Kumar, Jinjun Qiu +3

Current induced domain wall (DW) motion has been investigated in a 600-nm wide nanowire using multilayer film with a structure of Ta(5 nm)/Pd(5 nm)/[CoFe(0.4 nm)/Pd(1.2 nm)]

cs.DC2017

Enabling Massive Deep Neural Networks with the GraphBLAS

Jeremy Kepner, Manoj Kumar, José Moreira +3

Deep Neural Networks (DNNs) have emerged as a core tool for machine learning. The computations performed during DNN training and inference are dominated by operations on the weight…

cs.CR2007

Security Analysis of a Remote User Authentication Scheme with Smart Cards

Manoj Kumar

Yoon et al. proposed a new efficient remote user authentication scheme using smart cards to solve the security problems of W. C. Ku and S. M. Chen scheme. This paper reviews Yoon e…

cs.DB2013

Algorithm and approaches to handle large Data- A Survey

Chanchal Yadav, Shuliang Wang, Manoj Kumar

Data mining environment produces a large amount of data, that need to be analyzed, patterns have to be extracted from that to gain knowledge. In this new era with boom of data both…

cs.NI2013

DREAM_OLSR PROTOCOL (Distance Routing Effective Algorithm for Mobility - Optimized Link State Routing)

Gurpreet Singh Saini, Ashish Kots, Manoj Kumar

This paper lays down a proposal of protocol named DREAM_OLSR. The protocol has been developed so as to effect current OLSR (RFC 3626) [4] protocol. The protocol establishes an opti…

cs.CV2012

A New Approach of Improving CFA Image for Digital Camera's

Manoj Kumar, Vikas Kaushik, Pradeep Singla

This paper work directly towards the improving the quality of the image for the digital cameras and other visual capturing products. In this Paper, the authors clearly defines the…

cs.CV2024

Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations

Manoj Kumar, Neil Houlsby, Emiel Hoogeboom

Generating image variations, where a model produces variations of an input image while preserving the semantic context has gained increasing attention. Current image variation tech…

eess.AS2020

Multi-Scale Speaker Diarization With Neural Affinity Score Fusion

Tae Jin Park, Manoj Kumar, Shrikanth Narayanan

Identifying the identity of the speaker of short segments in human dialogue has been considered one of the most challenging problems in speech signal processing. Speaker representa…