arXiv subjects

Vikram Singh

Publications and source records attributed to Vikram Singh.

At least 19 recordsLinked to original sources

arXiv2026

Automated Video-to-QA Pipeline: End-to-End Question Generation and Verification Using Large Language Models

The exponential growth of educational and informational video content on platforms like YouTube presents a challenge for efficient knowledge retrieval and assessment. This paper proposes an end-to-end automated pipeline for extracting structured summaries and generating high-fidelity Question-Answer (QA) pairs from video streams. The framework integrates a cascade of state-of-the-art models: audio extraction is handled via FFmpeg, followed by automatic speech recognition (ASR) using Whisper (A library in Python) to generate accurate transcripts. Due to the token constraints of Large Language Models (LLMs), transcripts are segmented and summarized using Facebook's BART. A key innovation of this work is a Self-Verification and Fine-Tuning Loop. We utilize meta-llama/Llama-3.1-8BInstruct to generate candidate QA pairs from transcript chunks, which are then fed back into the model to rigorously assess their relevance and importance. Only verified, high-quality pairs are retained to construct a synthetic dataset. This dataset is subsequently used to fine-tune the Llama model using Low-Rank Adaptation (LoRA), resulting in a specialized model capable of generating domain-aligned assessment questions. This approach demonstrates a scalable method for creating self-improving educational tools without the need for manual data annotation. The proposed model can be downloaded from Kaggle with all the codes from GitHub.

cs.CL↗

arXiv2026

Learn the Interface, Not the Implementation: Output Representation Dominates Training Regime in LLM-Based RTL Generation

Large-language-model register-transfer-level (RTL) generation has concentrated on how to train the model: fine-tuning, continued pre-training, and reinforcement learning from a verifier. We argue this is the second-order question. On a bounded, formally specifiable task of generating single-error-correcting, double-error-detecting (SECDED) ECC memory wrappers, we hold the task, data, and correctness oracle fixed and vary two axes independently: the training regime (seven settings) and the output representation (four levels, from fully expanded flat Verilog to an eight-field configuration expanded by a deterministic generator). Because a reference generator exists, correctness is decided by formal equivalence over a design space of approximately ten million points, rather than sampled from a hand-written testbench. Two results follow. First, representation dominates: every representation close to raw RTL reaches a pass rate of at most 0.17, while the configuration reaches 0.83 with no training at all. Once the model emits the configuration, every training regime achieves a pass rate between 0.89 and 1.00. Second, raw RTL hits a hard output-length limit: a 512-bit design requires 44,237 tokens of flat Verilog compared with just 69 tokens for the configuration. Consequently, raw generation becomes infeasible above 32-bit data words rather than merely inaccurate. A model trained from scratch with fewer than 50 million parameters, combined with the verified generator, achieves 0.89 formal equivalence, compared with 1.00 for a 32-billion-parameter fine-tuned model, while using approximately 1600 times less inference energy per correct design. Inference energy also dominates amortized training energy. The lesson is to learn the interface, not the implementation.

cs.LG↗

arXiv2026

Performance evaluation of Secure DSRC (S-DSRC) protocol for Vehicular Adhoc Networks

Vehicular adhoc networks (VANETs) provides communication between the vehicles like V2V and also provides communication between the Vehicles and the Road side Units. Recently, VANETs have greater scope in establishing interconnectivity between the vehicles on road and off road. These networks ensure the timely report of accidents happening in highways, alerting the nearest hospital, insurance claims if the vehicle is breakdown, etc. Vehicles often travels in highways lack the network connectivity, which then can be ensured through many technology implementations like 4G, 5G, LTE networks and protocols like IEEE 802.11p and DSRC were helpful in achieving the effectiveness of vehicular networks. In this paper, we have proposed a protocol Secure Dedicated Short-Range Communication (S-DSRC) protocol that can establish connectivity between the vehicles in a secure way. There will be a secret key, private kay and public key exchange between the vehicles so that the safety message can be sent to vehicles in a secure way. Our results show that S-DSRC protocol outperforms the existing DSRC protocol for a medium sized network.

cs.NI↗

arXiv2026

Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling

Accurate localization of organ boundaries is critical in medical imaging for segmentation, registration, surgical planning, and radiotherapy. While deep convolutional networks (ConvNets) have advanced general-purpose edge detection to near-human performance on natural images, their outputs often lack precise localization, a limitation that is particularly harmful in medical applications where millimeter-level accuracy is required. Building on a systematic analysis of ConvNet edge outputs, we propose a medically focused crisp edge detector that adapts a novel top-down backward refinement architecture to medical images (2D and volumetric). Our method progressively upsamples and fuses high-level semantic features with fine-grained low-level cues through a backward refinement pathway, producing high-resolution, well-localized organ boundaries. We further extend the design to handle anisotropic volumes by combining 2D slice-wise refinement with light 3D context aggregation to retain computational efficiency. Evaluations on several CT and MRI organ datasets demonstrate substantially improved boundary localization under strict criteria (boundary F-measure, Hausdorff distance) compared to baseline ConvNet detectors and contemporary medical edge/contour methods. Importantly, integrating our crisp edge maps into downstream pipelines yields consistent gains in organ segmentation (higher Dice scores, lower boundary errors), more accurate image registration, and improved delineation of lesions near organ interfaces. The proposed approach produces clinically valuable, crisp organ edges that materially enhance common medical-imaging tasks.

cs.CV↗

arXiv2026

DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation

Lesion segmentation, in contrast to natural scene segmentation, requires handling subtle variations in texture and color, frequent imaging artifacts (such as hairs, rulers, and bubbles), and a critical need for precise boundary localization to aid in accurate diagnosis. The accurate delineation of melanocytic tumors in dermoscopic images is a crucial component of automated skin cancer screening systems and clinical decision support. In this paper, we present a novel dual-resolution architecture inspired by ResNet, specifically tailored for the segmentation of melanocytic tumors. Our approach incorporates a high-resolution stream that preserves fine boundary details, alongside a complementary pooled stream that captures multi-scale contextual information for robust lesion recognition. These two streams are closely integrated through boundary-aware residual connections, which inject edge information into deep feature maps, and a channel attention mechanism that adapts the model's sensitivity to color and texture variations in dermoscopic images. To tackle common imaging artifacts and the challenges posed by small clinical datasets, we introduce a lightweight artifact suppression block and a multi-task training strategy. This strategy combines the Dice-Tversky loss with an explicit boundary loss and a contrastive regularizer to enhance feature stability. This unified design enables the model to generate pixel-accurate segmentation masks without the need for extensive post-processing or complex pre-training. Extensive evaluation on public dermoscopic benchmarks reveals that our method significantly enhances boundary precision and clinically relevant segmentation metrics, outperforming traditional encoder-decoder baselines. This makes our approach a valuable component for building automated melanoma assessment systems.

cs.CV↗

arXiv2026

Cortex 2.0: Grounding World Models in Real-World Industrial Deployment

Industrial robotic manipulation demands reliable long-horizon execution across embodiments, tasks, and changing object distributions. While Vision-Language-Action models have demonstrated strong generalization, they remain fundamentally reactive. By optimizing the next action given the current observation without evaluating potential futures, they are brittle to the compounding failure modes of long-horizon tasks. Cortex 2.0 shifts from reactive control to plan-and-act by generating candidate future trajectories in visual latent space, scoring them for expected success and efficiency, then committing only to the highest-scoring candidate. We evaluate Cortex 2.0 on a single-arm and dual-arm manipulation platform across four tasks of increasing complexity: pick and place, item and trash sorting, screw sorting, and shoebox unpacking. Cortex 2.0 consistently outperforms state-of-the-art Vision-Language-Action baselines, achieving the best results across all tasks. The system remains reliable in unstructured environments characterized by heavy clutter, frequent occlusions, and contact-rich manipulation, where reactive policies fail. These results demonstrate that world-model-based planning can operate reliably in complex industrial environments.

cs.RO↗

arXiv2026

Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE

Fraud-related financial losses continue to rise, while regulatory, privacy, and data-sovereignty constraints increasingly limit the feasibility of centralized fraud detection systems. Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative model training across institutions without sharing raw transaction data. Yet, its practical effectiveness under realistic, non-IID financial data distributions remains insufficiently validated. In this work, we present a multi-institution, industry-oriented proof-of-concept study evaluating federated anomaly detection for payment transactions using the NVIDIA FLARE framework. We simulate a realistic federation of heterogeneous financial institutions, each observing distinct fraud typologies and operating under strict data isolation. Using a deep neural network trained via federated averaging (FedAvg), we demonstrate that federated models achieve a mean F1-score of 0.903 - substantially outperforming locally trained models (0.643) and closely approaching centralized training performance (0.925), while preserving full data sovereignty. We further analyze convergence behavior, showing that strong performance is achieved within 10 federated communication rounds, highlighting the operational viability of FL in latency- and cost-sensitive financial environments. To support deployment in regulated settings, we evaluate model interpretability using Shapley-based feature attribution and confirm that federated models rely on semantically coherent, domain-relevant decision signals. Finally, we incorporate sample-level differential privacy via DP-SGD and demonstrate favorable privacy-utility trade-offs...

cs.LG↗

arXiv2025

An Algorithm to Solve Cardinality Constrained Quadratic Optimization Problem with an Application to the Best Subset Selection in Regression

A lot of problems, from fields like sparse signal processing, statistics, portfolio selection, and machine learning, can be formulated as a cardinality constraint optimization problem. The cardinality constraint gives the problem a discrete nature, making it computationally challenging to solve as the dimension of the problem increases. In this work, we present an algorithm to solve the cardinality constraint quadratic optimization problem using the framework of the interval branch-and-bound. Interval branch-and-bound is a popular approach for finding a globally optimal solution in the field of global optimization. The proposed method is capable of solving problems of a wide range of dimensions. In particular, we solve the classical best subset selection problem in regression and compare our algorithm against another branch-and-bound method and GUROBI's quadratic mixed integer solver. Numerical results show that the proposed algorithm outperforms the first and is competitive with the second solver.

math.OC↗

arXiv2025

Solving the Best Subset Selection Problem via Suboptimal Algorithms

Best subset selection in linear regression is well known to be nonconvex and computationally challenging to solve, as the number of possible subsets grows rapidly with increasing dimensionality of the problem. As a result, finding the global optimal solution via an exact optimization method for a problem with dimensions of 1000s may take an impractical amount of CPU time. This suggests the importance of finding suboptimal procedures that can provide good approximate solutions using much less computational effort than exact methods. In this work, we introduce a new procedure and compare it with other popular suboptimal algorithms to solve the best subset selection problem. Extensive computational experiments using synthetic and real data have been performed. The results provide insights into the performance of these methods in different data settings. The new procedure is observed to be a competitive suboptimal algorithm for solving the best subset selection problem for high-dimensional data.

stat.ML↗

arXiv2024

Spin Squeezing with Magnetic Dipoles

Entanglement can improve the measurement precision of quantum sensors beyond the shot noise limit. Neutral atoms, the basis of some of the most precise and accurate optical clocks and interferometers, do not naturally exhibit all-to-all interactions that are traditionally used to generate such entangled states. Instead, we take advantage of the magnetic dipole-dipole interaction native to most neutral atoms to realize spin-squeezed states. We achieve 7.1 dB of metrologically useful squeezing using the finite-range spin exchange interactions in an erbium quantum gas microscope. We further propose and demonstrate that introducing atomic motion protects the spin sector coherence at low fillings, significantly improving the achievable spin squeezing in a 2D dipolar system. This work's protocol can be implemented with most neutral atoms, opening the door to quantum-enhanced metrology in other itinerant dipolar systems, such as molecules or optical lattice clocks, and serves as a novel method for studying itinerant quantum magnetism with long-range interactions.

quant-ph↗

arXiv2024

Revolutionizing Pharmaceutical Manufacturing: Advances and Challenges of 3D Printing System and Control

The advent of 3D printing has transformed the pharmaceutical industry, enabling precision drug manufacturing with controlled release profiles, dosing, and structural complexity. Additive manufacturing (AM) addresses the growing demand for personalized medicine, overcoming limitations of traditional methods. This technology facilitates tailored dosage forms, complex geometries, and real-time quality control. Recent advancements in drop-on-demand printing, UV curable inks, material science, and regulatory frameworks are discussed. Despite opportunities for cost reduction, flexibility, and decentralized manufacturing, challenges persist in scalability, reproducibility, and regulatory adaptation. This review provides an in-depth analysis of the current state of AM in pharmaceutical manufacturing, exploring recent developments, challenges, and future directions for mainstream integration.

eess.SY↗

arXiv2024

Double magnetic transition, complex field-induced phases, and large magnetocaloric effect in the frustrated garnet compound Mn$_{3}$Cr$_{2}$Ge$_{3}$O$_{12}$

A detailed study of the magnetic and magnetocaloric properties of a garnet compound Mn$_{3}$Cr$_{2}$Ge$_{3}$O$_{12}$ is carried out using x-ray diffraction, magnetization, heat capacity, and neutron diffraction measurements as well as \textit{ab initio} band-structure calculations. This compound manifests two successive magnetic transitions at $T_{\rm N1} \simeq 4.5$ K and $T_{\rm N2} \simeq 2.7$ K. Neutron powder diffraction experiments reveal that these two transitions correspond to the collinear and non-collinear antiferromagnetic ordering of the nonfrustrated Cr$^{3+}$ and frustrated Mn$^{2+}$ sublattices, respectively. The interactions within each of the Cr and Mn sublattices are antiferromagnetic, while the inter-sublattice interactions are ferromagnetic. The $H-T$ phase diagram is quite complex and displays multiple phases under magnetic field, which can be attributed to the frustrated nature of the spin lattice. Mn$_{3}$Cr$_{2}$Ge$_{3}$O$_{12}$ shows a large magnetocaloric effect with a maximum value of isothermal entropy change $ΔS_{\rm m} \simeq -23$ J/kg-K and adiabatic temperature change $ΔT_{\rm ad} \simeq 9$ K for a field change of 7 T. Further, a large value of the relative cooling power ($RCP \simeq 360$ J/kg) demonstrates the promise of using this compound in magnetic refrigeration.

cond-mat.str-el↗

arXiv2024

DeepAutoPIN: An automorphism orbits based deep neural network for characterizing the organizational diversity of protein interactomes across the tree of life

The enormous diversity of life forms thriving in drastically different environmental milieus involves a complex interplay among constituent proteins interacting with each other. However, the organizational principles characterizing the evolution of protein interaction networks (PINs) across the tree of life are largely unknown. Here we study 4,738 PINs belonging to 16 phyla to discover phyla-specific architectural features and examine if there are some evolutionary constraints imposed on the networks' topologies. We utilized positional information of a network's nodes by normalizing the frequencies of automorphism orbits appearing in graphlets of sizes 2-5. We report that orbit usage profiles (OUPs) of networks belonging to the three domains of life are contrastingly different not only at the domain level but also at the scale of phyla. Integrating the information related to protein families, domains, subcellular location, gene ontology, and pathways, our results indicate that wiring patterns of PINs in different phyla are not randomly generated rather they are shaped by evolutionary constraints imposed on them. There exist subtle but substantial variations in the wiring patterns of PINs that enable OUPs to differentiate among different superfamilies. A deep neural network was trained on differentially expressed orbits resulting in a prediction accuracy of 85%.

q-bio.MN↗

arXiv2024

Metal-Polypyridyl Complexes in Electronic Circuits

The integration of functional molecules onto conductive or dielectric surfaces represents a promising avenue for employing molecule-centric technologies, encompassing sensor development, electrochromic, and the facilitation of charge and spin transport at the nanoscale These assemblies exhibit robust physical and chemical stability, exerting influence not only on the interfacial properties of pertinent surfaces but also on the characteristics of the assembled molecules themselves. Within the spectrum of available molecules, metal-polypyridyl complexes have emerged as focal points of investigation for generating surface-bound assemblies, encompassing monolayers or multilayers, achieved through pre- or post-functionalization methodologies. The appeal of these complexes lies in their inherent versatility, stemming from facile synthesis, appreciable stability, and tunable properties encompassing redox behaviors, reactivity in excited states, luminescent emissions, excited state longevity, as well as responsiveness to stimuli-induced electron and energy transfer. This comprehensive review aims to delve into the nuanced traits and applications of surface-bound metal-polypyridyl complexes, elucidating their characteristics and practical implementations through pertinent and illustrative examples in the field of molecular electronics.

cond-mat.mtrl-sci↗

arXiv2023

Inferring interaction networks from transcriptomic data: methods and applications

Transcriptomic data is a treasure-trove in modern molecular biology, as it offers a comprehensive viewpoint into the intricate nuances of gene expression dynamics underlying biological systems. This genetic information must be utilised to infer biomolecular interaction networks that can provide insights into the complex regulatory mechanisms underpinning the dynamic cellular processes. Gene regulatory networks and protein-protein interaction networks are two major classes of such networks. This chapter thoroughly investigates the wide range of methodologies used for distilling insightful revelations from transcriptomic data that include association based methods (based on correlation among expression vectors), probabilistic models (using Bayesian and Gaussian models), and interologous methods. We reviewed different approaches for evaluating the significance of interactions based on the network topology and biological functions of the interacting molecules, and discuss various strategies for the identification of functional modules. The chapter concludes with highlighting network based techniques of prioritising key genes, outlining the centrality based, diffusion based and subgraph based methods. The chapter provides a meticulous framework for investigating transcriptomic data to uncover assembly of complex molecular networks for their adaptable analyses across a broad spectrum of biological domains.

q-bio.MN↗

arXiv2023

Resonant Ultrasound Spectroscopy of single crystalline KH$_{2}$PO$_{4}$

This study employs resonant ultrasound spectroscopy (RUS) to investigate the elastic properties of single crystalline KH$_{2}$PO$_{4}$ (KDP) through the paraelectric to ferroelectric phase transition. Noteworthy anomalies are observed in selected resonance modes and their corresponding mechanical quality factors ($Q$) around the transition temperature. The thermal evolution of elastic constants ($C_{ij}$) across the phase transition reveals a significant softening of $C_{11}$, $C_{12}$, and $C_{13}$, accompanied by a stiffening in $C_{66}$. Additionally, both $C_{33}$ and $C_{44}$ exhibit a minimum value at the transition. This anomalous behavior of all elastic constants ($C_{ij}$) across the phase transition suggests the involvement of higher-order coupling between the lattice and polarization in the KDP crystal. Furthermore, the bulk modulus ($B$) undergoes a sudden softening precisely at the transition, while the shear modulus ($G$) initially softens and subsequently stiffens across the transition.

cond-mat.str-el↗

arXiv2023

Large magnetocaloric effect in the kagome ferromagnet Li$_9$Cr$_3$(P$_2$O$_7$)$_3$(PO$_4$)$_2$

Single-crystal growth, magnetic properties, and magnetocaloric effect of the $S = 3/2$ kagome ferromagnet Li$_9$Cr$_3$(P$_2$O$_7$)$_3$(PO$_4$)$_2$ (trigonal, space group: $P\bar{3}c1$) are reported. Magnetization data suggest dominant ferromagnetic intra-plane coupling with a weak anisotropy and the onset of ferromagnetic ordering at $T_{\rm C} \simeq 2.6$ K. Microscopic analysis reveals a very small ratio of interlayer to intralayer ferromagnetic couplings ($J_{\perp}/J \simeq 0.02$). Electron spin resonance data suggest the presence of short-range correlations above $T_{\rm C}$ and confirms quasi-two-dimensional character of the spin system. A large magnetocaloric effect characterized by isothermal entropy change of $-ΔS_{\rm m}\simeq 31$ J kg$^{-1}$ K$^{-1}$ and adiabatic temperature change of $-ΔT_{\rm ad}\simeq 9$ K upon a field sweep of 7 T is observed around $T_{\rm C}$. This leads to a large relative cooling power of $RCP \simeq 284$ J kg$^{-1}$. The large magnetocaloric effect, together with negligible hysteresis render Li$_9$Cr$_3$(P$_2$O$_7$)$_3$(PO$_4$)$_2$ a promising material for magnetic refrigeration at low temperatures. The magnetocrystalline anisotropy constant $K \simeq -7.42 \times 10^4$ erg cm$^{-3}$ implies that the compound is an easy-plane type ferromagnet with the hard axis normal to the $ab$-plane, consistent with the magnetization data.

cond-mat.mtrl-sci↗

arXiv2022

Higher order organizational features can distinguish protein interaction networks of disease classes: a case study of neoplasms and neurological diseases

Neoplasms (NPs) and neurological diseases and disorders (NDDs) are amongst the major classes of diseases underlying deaths of a disproportionate number of people worldwide. To determine if there exist some distinctive features in the local wiring patterns of protein interactions emerging at the onset of a disease belonging to either of these two classes, we examined 112 and 175 protein interaction networks belonging to NPs and NDDs, respectively. Orbit usage profiles (OUPs) for each of these networks were enumerated by investigating the networks' local topology. 56 non-redundant OUPs (nrOUPs) were derived and used as network features for classification between these two disease classes. Four machine learning classifiers, namely, k-nearest neighbour (KNN), support vector machine (SVM), deep neural network (DNN), random forest (RF) were trained on these data. DNN obtained the greatest average AUPRC (0.988) among these classifiers. DNNs developed on node2vec and the proposed nrOUPs embeddings were compared using 5-fold cross validation on the basis of average values of the six of performance measures, viz., AUPRC, Accuracy, Sensitivity, Specificity, Precision and MCC. It was found that nrOUPs based classifier performed better in all of these six performance measures.

q-bio.MN↗