arXiv subjects

Lord Sen

Publications and source records attributed to Lord Sen.

5 recordsLinked to original sources

arXiv2026

Mapping Networks

The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting. We address this by introducing the \emph{Mapping Networks} which replace the high dimensional weight space by a compact, trainable latent vector based on the hypothesis that the trained parameters of large networks reside on smooth, low-dimensional manifolds. Henceforth, the Mapping Theorem enforced by a dedicated Mapping Loss, shows the existence of a mapping from this latent space to the target weight space both theoretically and in practice. Mapping Networks significantly reduce overfitting and achieve comparable to better performance than target network across complex vision and sequence tasks, including Image Classification, Deepfake Detection etc, with $\mathbf{99.5\%}$, i.e., around $500\times$ reduction in trainable parameters.

cs.CV↗

arXiv2026

A Novel Unified Approach to Deepfake Detection

The advancements in the field of AI is increasingly giving rise to various threats. One of the most prominent of them is the synthesis and misuse of Deepfakes. To sustain trust in this digital age, detection and tagging of deepfakes is very necessary. In this paper, a novel architecture for Deepfake detection in images and videos is presented. The architecture uses cross attention between spatial and frequency domain features along with a blood detection module to classify an image as real or fake. This paper aims to develop a unified architecture and provide insights into each step. Though this approach we achieve results better than SOTA, specifically 99.80%, 99.88% AUC on FF++ and Celeb-DF upon using Swin Transformer and BERT and 99.55, 99.38 while using EfficientNet-B4 and BERT. The approach also generalizes very well achieving great cross dataset results as well.

cs.CV↗

arXiv2025

Symmetric Reduction Techniques for Quantum Graph Colouring

This paper introduces an efficient quantum computing method for reducing special graphs in the context of the graph coloring problem. The special graphs considered include both symmetric and non-symmetric graphs where the axis passes through nodes only, edges only, and both together. The presented method reduces the number of coloring matrices, which is important for realization of the number of quantum states required, from $K^{N}$ to $K^{\frac{N+m}{2}}$ upon one symmetric reduction of graphs symmetric about an axis passing through $m$ nodes, where $K$ is the number of colours required and \emph{N} being total number of nodes. Similarly for other types also, the number of quantum states is reduced. The complexity in the number of qubits has been reduced by $\delta C_q= \frac{9N^2}{8}-\frac{3m^2}{8}-\frac{3Nm}{4}-\frac{N}{4}+\frac{m}{4}$ upon one symmetric reduction of graphs, symmetric about an axis passing through $m$ nodes and other types as presented in the paper. Additionally, the number of gates and number of iterations are reduced massively compared to state-of-the-art quantum algorithms. Like for a graph with 20 nodes and symmetric line passing through 2 nodes, the number of iterations decreased from 5157 to 67. Therefore, the procedure presented for solving the graph coloring problem now requires a significantly reduced number of qubits compared to before. The run time of the proposed algorithm for these special type of graphs are reduced from $O(1.9575^{N})$ to $O(1.9575^{(\frac{N+m}{2})})$ upon one symmetric reduction of graphs symmetric about an axis passing through $m$ nodes and similarly for others cases.

quant-ph↗

arXiv2025

QuIRK: Quantum-Inspired Re-uploading KAN

Kolmogorov-Arnold Networks or KANs have shown the ability to outperform classical Deep Neural Networks, while using far fewer trainable parameters for regression problems on scientific domains. Even more powerful has been their interpretability due to their structure being composed of univariate B-Spline functions. This enables us to derive closed-form equations from trained KANs for a wide range of problems. This paper introduces a quantum-inspired variant of the KAN based on Quantum Data Re-uploading (DR) models. The Quantum-Inspired Re-uploading KAN or QuIRK model replaces B-Splines with single-qubit DR models as the univariate function approximator, allowing them to match or outperform traditional KANs while using even fewer parameters. This is especially apparent in the case of periodic functions. Additionally, since the model utilizes only single-qubit circuits, it remains classically tractable to simulate with straightforward GPU acceleration. Finally, we also demonstrate that QuIRK retains the interpretability advantages and the ability to produce closed-form solutions.

quant-ph↗

arXiv2023

QPMeL - Quantum-Aware Classically-Trained Embeddings via Projective Metric Learning

Deep metric learning has recently shown extremely promising results in the classical data domain, creating well-separated feature spaces. This idea was also adapted to quantum computers via Quantum Metric Learning(QMeL). QMeL consists of a 2-step process with a classical model to compress the data to fit into the limited number of qubits, then train a Parameterized Quantum Circuit(PQC) to create better separation in Hilbert Space. However, on Noisy Intermediate Scale Quantum (NISQ) devices. QMeL solutions result in high circuit width and depth, both of which limit scalability. We propose Quantum Polar Metric Learning (QPMeL) that uses a classical model to learn the parameters of the polar form of a qubit. We then utilize a shallow PQC with $R_y$ and $R_z$ gates to create the state and a trainable layer of $ZZ(\theta)$-gates to learn entanglement. The circuit also computes fidelity via a SWAP Test for our proposed Fidelity Triplet Loss function, used to train both classical and quantum components. When compared to QMeL approaches, QPMeL achieves 3X better multi-class separation, while using only 1/2 the number of gates and depth. We also demonstrate that QPMeL outperforms classical networks with similar configurations, presenting a promising avenue for future research on fully classical models with quantum loss functions.

quant-ph↗