Searcharxiv⌕ Search

arXiv subjects

Himanshu Singh

Publications and source records attributed to Himanshu Singh.

17 recordsLinked to original sources
arXiv2026

Which Anatomy Matters Under Limited Labels? A Data-Efficient Anatomy-Aware Benchmark for Cardiac Pathology Prediction

Numerous medical imaging problems must be solved under limited labels and constrained compute, yet it remains unclear whether performance gains are driven mainly by more expressive models or by better representation of clinically meaningful anatomy. We study this question through a low-data anatomy-aware benchmark for 5-class cardiac pathology prediction on the public ACDC MRI dataset. Using segmentation-derived patient descriptors from the right ventricle, myocardium, and left ventricle, we compare anatomy-specific and multi-structure representations across linear, kernel, and tree-based classifiers. We find that under limited label settings, representation dominates complexity. These results suggest that in resource-constrained healthcare settings, identifying and representing the most informative anatomy may matter more than the increasing complexity of the model alone.

eess.IV↗
arXiv2026

Nearest Neighbor Projection Removal Adversarial Training

Deep neural networks have exhibited impressive performance in image classification tasks but remain vulnerable to adversarial examples. Standard adversarial training enhances robustness but typically fails to explicitly address inter-class feature overlap, a significant contributor to adversarial susceptibility. In this work, we introduce a novel adversarial training framework that actively mitigates inter-class proximity by projecting out inter-class dependencies from adversarial and clean samples in the feature space. Specifically, our approach first identifies the nearest inter-class neighbors for each adversarial sample and subsequently removes projections onto these neighbors to enforce stronger feature separability. Theoretically, we demonstrate that our proposed logits correction reduces the Lipschitz constant of neural networks, thereby lowering the Rademacher complexity, which directly contributes to improved generalization and robustness. Extensive experiments across standard benchmarks including CIFAR-10, CIFAR-100, SVHN, and TinyImagenet show that our method demonstrates strong performance that is competitive with leading adversarial training techniques, highlighting significant achievements in both robust and clean accuracy. Our findings reveal the importance of addressing inter-class feature proximity explicitly to bolster adversarial robustness in DNNs. The code is available in the supplementary material.

cs.CV↗
arXiv2026

Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often subtle and context-dependent, making it difficult to detect at the token level or through coarse sentence-level signals. Moreover, efforts to mitigate toxicity often face a trade-off between safety and the coherence, or fluency of the generated text. In this work, we present a targeted subspace intervention strategy for identifying and suppressing hidden toxic patterns from underlying model representations, while preserving overall ability to generate safe fluent content. On the RealToxicityPrompts, our method achieves strong mitigation performance compared to existing baselines, with minimal impact on inference complexity. Across multiple LLMs, our approach reduces toxicity of state-of-the-art detoxification systems by 8-20%, while maintaining comparable fluency. Through extensive quantitative and qualitative analyses, we show that our approach achieves effective toxicity reduction without impairing generative performance, consistently outperforming existing baselines.

cs.CL↗
arXiv2026

An IoT-Based Controlled Environment Storage for Prevention of Spoilage of Onion (Allium Cepa) During Post-Harvest with UV-C Disinfection

India is the second largest producer of onions in the world, contributing over 26 million tonnes annually. However, during storage, approximately 30-40% of onions are lost due to rotting, sprouting, and weight loss. Despite being a major producer, conventional storage methods are either low-cost but ineffective (traditional storage with 40% spoilage) or highly effective but prohibitively expensive for small farmers (cold storage). This paper presents a low-cost IoT-based smart onion storage system that monitors and automatically regulates environmental parameters including temperature, humidity, and spoilage gases using ESP32 microcontroller, DHT22 sensor, MQ-135 gas sensor, and UV-C disinfection technology. The proposed system aims to reduce onion spoilage to 15-20% from the current 40-45% wastage rate while remaining affordable for small and marginal farmers who constitute the majority in India. The system is designed to be cost-effective (estimated 60k-70k INR), energy-efficient, farmer-friendly, and solar-powered.

eess.SP↗
arXiv2026

Temporal Graph Network: Hallucination Detection in Multi-Turn Conversation

Hallucinations can be produced by conversational AI systems, particularly in multi-turn conversations where context changes and contradictions may eventually surface. By representing the entire conversation as a temporal graph, we present a novel graph-based method for detecting dialogue-level hallucinations. Our framework models each dialogue as a node, encoding it using a sentence transformer. We explore two different ways of connectivity: i) shared-entity edges, which connect turns that refer to the same entities; ii) temporal edges, which connect contiguous turns in the conversation. Message-passing is used to update the node embeddings, allowing flow of information between related nodes. The context-aware node embeddings are then combined using attention pooling into a single vector, which is then passed on to a classifier to determine the presence and type of hallucinations. We demonstrate that our method offers slightly improved performance over existing methods. Further, we show the attention mechanism can be used to justify the decision making process. The code and model weights are made available at: https://github.com/sambuaneesh/anlp-project.

cs.CL↗
arXiv2025

Kinetic Monte Carlo prediction of the morphology of pentaerythritol tetranitrate

In this work, we develop an atomistic, graph-based kinetic Monte Carlo (KMC) simulation routine to predict crystal morphology. Within this routine, we encode the state of the supercell in a binary occupation vector and the topology of the supercell in a simple nearest-neighbor graph. From this encoding, we efficiently compute the interaction energy of the system as a quadratic form of the binary occupation vector, representing pairwise interactions. This encoding, coupled with a simple diffusion model for adsorption, is then used to model evaporation and adsorption dynamics at solid-liquid interfaces. The resulting intermolecular interaction-breaking energies are incorporated into a kinetic model to predict crystal morphology, which is implemented in the open-source Python package Crystal Growth Kinetic Monte Carlo (cgkmc). We then apply this routine to pentaerythritol tetranitrate (PETN), an important energetic material, showing excellent agreement with the attachment energy model.

cond-mat.mtrl-sci↗
arXiv2025

Kernel Dynamic Mode Decomposition For Sparse Reconstruction of Closable Koopman Operators

Spatial temporal reconstruction of dynamical system is indeed a crucial problem with diverse applications ranging from climate modeling to numerous chaotic and physical processes. These reconstructions are based on the harmonious relationship between the Koopman operators and the choice of dictionary, determined implicitly by a kernel function. This leads to the approximation of the Koopman operators in a reproducing kernel Hilbert space (RKHS) associated with that kernel function. Data-driven analysis of Koopman operators demands that Koopman operators be closable over the underlying RKHS, which still remains an unsettled, unexplored, and critical operator-theoretic challenge. We aim to address this challenge by investigating the embedding of the Laplacian kernel in the measure-theoretic sense, giving rise to a rich enough RKHS to settle the closability of the Koopman operators. We leverage Kernel Extended Dynamic Mode Decomposition with the Laplacian kernel to reconstruct the dominant spatial temporal modes of various diverse dynamical systems. After empirical demonstration, we concrete such results by providing the theoretical justification leveraging the closability of the Koopman operators on the RKHS generated by the Laplacian kernel on the avenues of Koopman mode decomposition and the Koopman spectral measure. Such results were explored from both grounds of operator theory and data-driven science, thus making the Laplacian kernel a robust choice for spatial-temporal reconstruction.

math.DS↗
arXiv2023

Data-driven discovery with Limited Data Acquisition for fluid flow across cylinder

One of the central challenge for extracting governing principles of dynamical system via Dynamic Mode Decomposition (DMD) is about the limit data availability or formally called as Limited Data Acquisition in the present paper. In the interest of discovering the governing principles for a dynamical system with limited data acquisition, we provide a variant of Kernelized Extended DMD (KeDMD) based on the Koopman operator which employ the notion of Gaussian random matrix to recover the dominant Koopman modes for the standard fluid flow across cylinder experiment. It turns out that the traditional kernel function, Gaussian Radial Basis Function Kernel, unfortunately, is not able to generate the desired Koopman modes in the scenario of executing KeDMD with limited data acquisition. However, the Laplacian Kernel Function successfully generates the desired Koopman modes when limited data is provided in terms of data-set snapshot for the aforementioned experiment and this manuscripts serves the purpose of reporting these exciting experimental insights. This paper also explores the functionality of the Koopman operator when it interacts with the reproducing kernel Hilbert space (RKHS) that arises from the normalized probability Lebesgue measure $dμ_{σ,1,\mathbb{C}^n}(z)=(2πσ^2)^{-n}\exp\left(-\frac{\|z\|_2}σ\right)dV(z)$ when it is embedded in $L^2-$sense for the holomorphic functions over $\mathbb{C}^n$, in the aim of determining the Koopman modes for fluid flow across cylinder experiment. We explore the operator-theoretic characterizations of the Koopman operator on the RKHS generated by the normalized Laplacian measure $dμ_{σ,1,\mathbb{C}^n}(z)$ in the $L^2-$sense. In doing so, we provide the compactification & closable characterization of Koopman operator over the RKHS generated by the normalized Laplacian measure in the $L^2-$sense.

math.DS↗
arXiv2023

An appointment with Reproducing Kernel Hilbert Space generated by Generalized Gaussian RBF as $L^2-$measure

Gaussian Radial Basis Function (RBF) Kernels are the most-often-employed kernels in artificial intelligence and machine learning routines for providing optimally-best results in contrast to their respective counter-parts. However, a little is known about the application of the Generalized Gaussian Radial Basis Function on various machine learning algorithms namely, kernel regression, support vector machine (SVM) and pattern-recognition via neural networks. The results that are yielded by Generalized Gaussian RBF in the kernel sense outperforms in stark contrast to Gaussian RBF Kernel, Sigmoid Function and ReLU Function. This manuscript demonstrates the application of the Generalized Gaussian RBF in the kernel sense on the aforementioned machine learning routines along with the comparisons against the aforementioned functions as well.

cs.LG↗
arXiv2023

Language Guided Adversarial Purification

Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion and score networks have improved image generation and, by extension, adversarial purification. Another highly efficient class of adversarial defense methods known as adversarial training requires specific knowledge of attack vectors, forcing them to be trained extensively on adversarial examples. To overcome these limitations, we introduce a new framework, namely Language Guided Adversarial Purification (LGAP), utilizing pre-trained diffusion models and caption generators to defend against adversarial attacks. Given an input image, our method first generates a caption, which is then used to guide the adversarial purification process through a diffusion network. Our approach has been evaluated against strong adversarial attacks, proving its effectiveness in enhancing adversarial robustness. Our results indicate that LGAP outperforms most existing adversarial defense techniques without requiring specialized network training. This underscores the generalizability of models trained on large datasets, highlighting a promising direction for further research.

cs.LG↗
arXiv2023

Learning Neuro-symbolic Programs for Language Guided Robot Manipulation

Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on hand-coded symbols for concepts limiting generalization beyond those seen during training [1] (ii) infer action sequences from instructions but require dense sub-goal supervision [2] or (iii) lack semantics required for deeper object-centric reasoning inherent in interpreting complex instructions [3]. In contrast, our approach can handle linguistic as well as perceptual variations, end-to-end trainable and requires no intermediate supervision. The proposed model uses symbolic reasoning constructs that operate on a latent neural object-centric representation, allowing for deeper reasoning over the input scene. Central to our approach is a modular structure consisting of a hierarchical instruction parser and an action simulator to learn disentangled action representations. Our experiments on a simulated environment with a 7-DOF manipulator, consisting of instructions with varying number of steps and scenes with different number of objects, demonstrate that our model is robust to such variations and significantly outperforms baselines, particularly in the generalization settings. The code, dataset and experiment videos are available at https://nsrmp.github.io

cs.RO↗
arXiv2022

A Methodology to Generate Crystal-based Molecular Structures for Atomistic Simulations

We propose a systematic method to construct crystal-based molecular structures often needed as input for computational chemistry studies. These structures include crystal ``slabs" with periodic boundary conditions (PBCs) and non-periodic solids such as Wulff structures. We also introduce a method to build crystal slabs with orthogonal PBC vectors. These methods are integrated into our code, Los Alamos Crystal Cut (LCC), which is open source and thus fully available to the community. Examples showing the use of these methods are given throughout the manuscript.

cond-mat.mtrl-sci↗
arXiv2021

The trifecta of Hilbert spaces on Unit Disc

The Hilbert spaces are common. But the direct connection between them is rare. The aim of this paper is to establish a direct relation among the three Hilbert spaces Hardy, Bergman and Dirichlet without defining any of the Hilbert space in weighted sense. In order to accomplish this goal, this paper develops the Littlewood-Paley type Identities for Bergman and Dirichlet space. After defining these identities, the vision of connecting all the three Hilbert spaces via a direct connection is achieved.

math.FA↗
arXiv2021

Polylogarithmic Hardy space & its Nevanlinna counting function

We present the upper bound of the essential norm of the composition operator over the Polylogarithmic Hardy space PL2(D;s).The results involve the Nevanlinna counting function for PL2(D;s). We first prove the Littlewood-Paley Identity for PL2(D;s) which leads to the Nevanlinna counting function for PL2(D;s). With all these results, not only we get the upper bound of the essential norm of the composition operator over PL2(D;s) but also we get an upper bound in terms of the angular derivative and essential norm of composition operator over the Hardy space H2.

math.FA↗
arXiv2021

The Mittag Leffler space & its Littlewood-Paley Identity

We present the Littlewood-Paley Identity for the Mittag-Leffler space ML2(C; α) of entire functions. We also briefly demonstrate the connection between the Littlewood-Paley Identity and the compactness of the weighted composition operator on ML2(C; α).

math.CV↗
arXiv2021

Weighted Composition Operator and the Mittag-Leffler space

We present important characterizations of the Weighted Composition Operator over the Mittag Leffler space of entire functions. These characterizations include the Hilbert-Schmidt and Unitary char-acterizations of the Weighted Composition Operator over the Mittag-Leffler space. We also see the result for the spectrum of Weighted com-position operator over the Mittag-Leffler space

math.FA↗