arXiv subjects

Himanshu Singhal

Publications and source records attributed to Himanshu Singhal.

4 recordsLinked to original sources

arXiv2026

GAFSV-Net: A Vision Framework for Online Signature Verification

Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few enrollment samples. Existing deep learning methods operate directly on raw temporal sequences, restricting them to 1D architectures and preventing the use of pretrained 2D vision backbones. We bridge this gap with GAFSV-Net, which represents each signature as a six-channel asymmetric Gramian Angular Field image: three kinematic channels (pen speed, pressure derivative, direction angle) are each encoded into complementary GASF and GADF matrices that capture pairwise temporal co-occurrence and directional transition structure respectively. A dual-branch ConvNeXt-Tiny encoder processes GASF and GADF independently, with bidirectional cross-attention enabling each branch to query discriminative patterns from the other before metric-space projection. Training uses semi-hard triplet loss with skilled-forgery hard-negative injection; verification is performed via cosine similarity against a small enrollment prototype. We evaluate on DeepSignDB and BiosecurID, outperforming all sequence-based baselines trained under identical objectives, demonstrating that the representational gain of 2D temporal encoding is consistent and independent of training procedure, with ablations characterising each design choice's contribution.

cs.CV↗

arXiv2025

REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval

Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table table compatibility. We introduce REAR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REAR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REAR is retriever-agnostic and consistently improves dense/sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g.,ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REAR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).

cs.IR↗

arXiv2025

Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space

Zero-day anomaly detection is critical in industrial applications where novel, unforeseen threats can compromise system integrity and safety. Traditional detection systems often fail to identify these unseen anomalies due to their reliance on in-distribution data. Domain generalization addresses this gap by leveraging knowledge from multiple known domains to detect out-of-distribution events. In this work, we introduce a multi-task representation learning technique that fuses information across related domains into a unified latent space. By jointly optimizing classification, reconstruction, and mutual information regularization losses, our method learns a minimal(bottleneck), domain-invariant representation that discards spurious correlations. This latent space decorrelation enhances generalization, enabling the detection of anomalies in unseen domains. Our experimental results demonstrate significant improvements in zero-day or novel anomaly detection across diverse anomaly detection datasets.

cs.CR↗

arXiv2015

New frontier of laser particle acceleration: driving protons to 93 MeV by radiation pressure

The radiation pressure acceleration (RPA) of charged particles has been considered a challenging task in laser particle acceleration. Laser-driven proton/ion acceleration has attracted considerable interests due to its underlying physics and potential for applications such as high-energy density physics, ultrafast radiography, and cancer therapy. Among critical issues to overcome the biggest challenge is to produce energetic protons using an efficient acceleration mechanism. The proton acceleration by radiation pressure is considerably more efficient than the conventional target normal sheath acceleration driven by expanding hot electrons. Here we report the generation of 93-MeV proton beams achieved by applying 30-fs circularly polarized laser pulses with an intensity of 6.1 x 1020 W/cm2 to ultrathin targets. The radiation pressure acceleration was confirmed from the obtained optimal target thickness, quadratic energy scaling, polarization dependence, and 3D-PIC simulations. We expect this fast energy scaling to facilitate the realization of laser-driven proton/ion sources delivering stable and short particle beams for practical applications.

physics.plasm-ph↗