arXiv subjects

Akash Das

Publications and source records attributed to Akash Das.

12 recordsLinked to original sources

arXiv2026

Basis-Independent Geometric Phase Modulation in Circularly Birefringent Plasmonic Structures

Geometric phase in metasurfaces is conventionally realized using spatially rotated linearly birefringent meta-atoms under circularly polarized illumination. Here we demonstrate that full $\sim2\pi$ geometric phase modulation can be achieved through circular birefringence and observed under linear polarization excitation. We introduce a plasmonic metasurface composed of spatially rotated chiral spiral unit cells designed to produce space-variant circular retardance. This generates a geometric phase ramp equivalent to a blazed grating, leading to $\pm1$ diffraction orders in momentum space. Using leakage radiation microscopy, we directly resolve these orders and show how their intensities depend upon the input linear polarization confirming the geometric origin of the phase. We theoretically analyze the phenomenon using a rotated Poincar\'{e} space and confirm our results by direct Stokes parameters measurement. These results establish basis-independent approach to geometric phase accumulation in circularly birefringent plasmonic metasurfaces.

physics.optics↗

arXiv2026

Statistical properties of non-flow correlations in pp and heavy-ion collisions at RHIC energies

In this work, we have studied the two-particle cumulant in pp, d-Au, and Au-Au collisions. The two-particle cumulant was treated as an event-by-event distribution, and its skewness and kurtosis were analyzed. The non-flow correlations, like jets and decays, constantly produced a skewed distribution, regardless of the model used. On the contrary, HYDJET++ produced a smooth Gaussian distribution at higher $\eta$ windows in fixed impact parameter collisions. The skewness increased consistently for higher $\eta$ windows in all non-QGP models like PYTHIA, PHOJET, QGSJET, and DPMJET. The kurtosis of the distribution also increased with $\eta$ windows in non-QGP models. The skewness and kurtosis of the distributions produced by HYDJET++ decreased with $\Delta\eta$ and eventually reached zero at higher $\Delta\eta$.

nucl-th↗

arXiv2025

Physics-informed neural network (PINN) modeling of charged particle multiplicity using the two-component framework in heavy-ion collisions: A comparison with data-driven neural networks

In this study, we employ a conventional deep neural network (NN) framework integrated with physics-based constraints to predict charged hadron multiplicity ($N_{\text{ch}}$) in heavy-ion collisions. The goal is to assess the performance of a purely data-driven deep neural network in comparison to a physics-informed neural network (PINN). To accomplish this, we have taken data generated from the HYDJET++ model for testing and training purposes. We train our neural network frameworks using the data of one million individual $^{96}_{40}\text{Zr}+^{96}_{40}\text{Zr}$ collision events. Our PINN model successfully extracts the hard-scattering fraction ($x$) by learning its underlying relation from the event data. For further testing and comparison with the conventional NN, we take data of $^{96}_{44}\text{Ru}+^{96}_{44}\text{Ru}$ (isobar of Zr) and $^{197}_{79}\text{Au}+^{197}_{79}\text{Au}$ collisions using the same simulation model. We found that the NN model needs more time to train with physics. However, once trained, the PINN model is capable of accurately predicting data that it has not encountered during training, such as Au+Au collision results. Especially in a region of sparse data corresponding to high $N_{\text{ch}}$ in our study, PINN has a clear advantage over a simple NN.

hep-ph↗

arXiv2025

Effects of Geometric configuration in relativistic isobaric collisions at $\sqrt{s_{NN}}=200$ GeV

In this work, we present a study on the effects of nuclear deformation ($\beta_2$,$\beta_3$) and surface diffuseness ($a$) on the charged hadron multiplicity ($N_{\mathrm{ch}}$) and elliptic flow ($v_2$), obtained in symmetric isobaric collisions of ${}^{96}_{44}\mathrm{Ru} + {}^{96}_{44}\mathrm{Ru}$ and ${}^{96}_{40}\mathrm{Zr} + {}^{96}_{40}\mathrm{Zr}$. The two extreme configurations (tip-tip and body-body) were used to determine the correlation between the final state observables and initial geometry using the HYDJET++ model. The octupole deformation parameter ($\beta_3$) enhances $N_{\mathrm{ch}}$ in central tip-tip Zr+Zr collisions and suppresses it in peripheral ones. In mid-central to peripheral body-body Zr+Zr collisions, $\beta_3$ leads to a reduction in charged hadron production. Surface-diffuseness ($a$), along with quadrapole deformation ($\beta_2$), also shows a significant impact on multiplicity and elliptic flow. The octupole deformation enhances elliptic flow in Zr's body-body collisions. Results are compared with the STAR blind-analysis data where available.

nucl-th↗

arXiv2025

Two-particle cumulant distribution: a simulation study of higher moments

In this work, we have shown the two-particle correlations of charged hadrons in d-Au collisions at 200 GeV in PYTHIA8/Angantyr simulations. These correlations were studied at different multiplicities and pseudorapidity intervals. The two-particle correlations arise due to color reconnections, resonance decays, jet correlations, and hadronic rescattering. These correlations are inversely proportional to multiplicity but remain unaffected for larger pseudorapidity windows. We treated these correlations as distributions and calculated their skewness and kurtosis. The non-flow distributions deviate greatly from a Gaussian distribution and have high skewness and kurtosis. The ``true" elliptic flow distributions resemble Gaussian distributions; they have significantly lower skewness and kurtosis. We suggest that if the two-particle cumulant flow is treated as an event-by-event distribution, its skewness and kurtosis can be instrumental in distinguishing true flow and non-flow.

hep-ph↗

arXiv2025

Optimizing Deep Learning for Skin Cancer Classification: A Computationally Efficient CNN with Minimal Accuracy Trade-Off

The rapid advancement of deep learning in medical image analysis has greatly enhanced the accuracy of skin cancer classification. However, current state-of-the-art models, especially those based on transfer learning like ResNet50, come with significant computational overhead, rendering them impractical for deployment in resource-constrained environments. This study proposes a custom CNN model that achieves a 96.7\% reduction in parameters (from 23.9 million in ResNet50 to 692,000) while maintaining a classification accuracy deviation of less than 0.022\%. Our empirical analysis of the HAM10000 dataset reveals that although transfer learning models provide a marginal accuracy improvement of approximately 0.022\%, they result in a staggering 13,216.76\% increase in FLOPs, considerably raising computational costs and inference latency. In contrast, our lightweight CNN architecture, which encompasses only 30.04 million FLOPs compared to ResNet50's 4.00 billion, significantly reduces energy consumption, memory footprint, and inference time. These findings underscore the trade-off between the complexity of deep models and their real-world feasibility, positioning our optimized CNN as a practical solution for mobile and edge-based skin cancer diagnostics.

eess.IV↗

arXiv2025

Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on knowledge-intensive tasks, including opendomain question answering and complex reasoning. Our framework integrates two complementary techniques: Policy-Optimized RetrievalAugmented Generation (PORAG), which optimizes the use of retrieved information, and Adaptive Token-Layer Attention Scoring (ATLAS), which dynamically determines retrieval timing and content based on contextual needs. Together, these techniques enhance both the utilization and relevance of retrieved content, improving factual accuracy and response quality. Designed as a lightweight solution compatible with any Transformer-based LLM without requiring additional training, our framework excels in knowledge-intensive tasks, boosting output accuracy in RAG settings. We further propose CRITIC, a novel method to selectively compress key-value caches by token importance, mitigating memory bottlenecks in long-context applications. The framework also incorporates test-time scaling techniques to dynamically balance reasoning depth and computational resources, alongside optimized decoding strategies for faster inference. Experiments on benchmark datasets show that our framework reduces hallucinations, strengthens domain-specific reasoning, and achieves significant efficiency and scalability gains over traditional RAG systems. This integrated approach advances the development of robust, efficient, and scalable RAG systems across diverse applications.

cs.LG↗

arXiv2025

Agentic Multimodal AI for Hyperpersonalized B2B and B2C Advertising in Competitive Markets: An AI-Driven Competitive Advertising Framework

The growing use of foundation models (FMs) in real-world applications demands adaptive, reliable, and efficient strategies for dynamic markets. In the chemical industry, AI-discovered materials drive innovation, but commercial success hinges on market adoption, requiring FM-driven advertising frameworks that operate in-the-wild. We present a multilingual, multimodal AI framework for autonomous, hyper-personalized advertising in B2B and B2C markets. By integrating retrieval-augmented generation (RAG), multimodal reasoning, and adaptive persona-based targeting, our system generates culturally relevant, market-aware ads tailored to shifting consumer behaviors and competition. Validation combines real-world product experiments with a Simulated Humanistic Colony of Agents to model consumer personas, optimize strategies at scale, and ensure privacy compliance. Synthetic experiments mirror real-world scenarios, enabling cost-effective testing of ad strategies without risky A/B tests. Combining structured retrieval-augmented reasoning with in-context learning (ICL), the framework boosts engagement, prevents market cannibalization, and maximizes ROAS. This work bridges AI-driven innovation and market adoption, advancing multimodal FM deployment for high-stakes decision-making in commercial marketing.

cs.LG↗

arXiv2025

Separating non-collective effects in d-Au collisions

In this work, we present the multiplicity and yield of charged hadrons and particle ratios in d-Au collisions at $\sqrt{s_{NN}}= 200$ GeV using the PYTHIA8/Angantyr. The model reproduces the multiplicity ($N_{ch}$) and pseudo-rapidity distribution reasonably well in minimum-biased d-Au collisions without assuming the formation of a thermalized medium. The invariant yield from Angantyr underpredicts the data in central collisions. We discussed the similarity between the nuclear modification factor $R_{AA}$ and data/MC from Angantyr and the possibility of using it as a model-dependent observable to check in-medium effects. The data/MC suggests that the central d-Au collisions exhibit signals like baryon enhancement, but no high $p_T$ suppression was found. The d-Au collisions have a much smaller invariant yield than the thermal model calculation for similar $N_{part}$.

nucl-th↗

arXiv2024

Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design

Process Flow Diagrams (PFDs) and Process and Instrumentation Diagrams (PIDs) are critical tools for industrial process design, control, and safety. However, the generation of precise and regulation-compliant diagrams remains a significant challenge, particularly in scaling breakthroughs from material discovery to industrial production in an era of automation and digitalization. This paper introduces an autonomous agentic framework to address these challenges through a twostage approach involving knowledge acquisition and generation. The framework integrates specialized sub-agents for retrieving and synthesizing multimodal data from publicly available online sources and constructs ontological knowledge graphs using a Graph Retrieval-Augmented Generation (Graph RAG) paradigm. These capabilities enable the automation of diagram generation and open-domain question answering (ODQA) tasks with high contextual accuracy. Extensive empirical experiments demonstrate the frameworks ability to deliver regulation-compliant diagrams with minimal expert intervention, highlighting its practical utility for industrial applications.

cs.LG↗

arXiv2020

Depression Status Estimation by Deep Learning based Hybrid Multi-Modal Fusion Model

Preliminary detection of mild depression could immensely help in effective treatment of the common mental health disorder. Due to the lack of proper awareness and the ample mix of stigmas and misconceptions present within the society, mental health status estimation has become a truly difficult task. Due to the immense variations in character level traits from person to person, traditional deep learning methods fail to generalize in a real world setting. In our study we aim to create a human allied AI workflow which could efficiently adapt to specific users and effectively perform in real world scenarios. We propose a Hybrid deep learning approach that combines the essence of one shot learning, classical supervised deep learning methods and human allied interactions for adaptation. In order to capture maximum information and make efficient diagnosis video, audio, and text modalities are utilized. Our Hybrid Fusion model achieved a high accuracy of 96.3% on the Dataset; and attained an AUC of 0.9682 which proves its robustness in discriminating classes in complex real-world scenarios making sure that no cases of mild depression are missed during diagnosis. The proposed method is deployed in a cloud-based smartphone application for robust testing. With user-specific adaptations and state of the art methodologies, we present a state-of-the-art model with user friendly experience.

cs.LG↗

arXiv2020

A Data-Efficient Deep Learning Based Smartphone Application For Detection Of Pulmonary Diseases Using Chest X-rays

This paper introduces a paradigm of smartphone application based disease diagnostics that may completely revolutionise the way healthcare services are being provided. Although primarily aimed to assist the problems in rendering the healthcare services during the coronavirus pandemic, the model can also be extended to identify the exact disease that the patient is caught with from a broad spectrum of pulmonary diseases. The app inputs Chest X-Ray images captured from the mobile camera which is then relayed to the AI architecture in a cloud platform, and diagnoses the disease with state of the art accuracy. Doctors with a smartphone can leverage the application to save the considerable time that standard COVID-19 tests take for preliminary diagnosis. The scarcity of training data and class imbalance issues were effectively tackled in our approach by the use of Data Augmentation Generative Adversarial Network (DAGAN) and model architecture based as a Convolutional Siamese Network with attention mechanism. The backend model was tested for robustness us-ing publicly available datasets under two different classification scenarios(Binary/Multiclass) with minimal and noisy data. The model achieved pinnacle testing accuracy of 99.30% and 98.40% on the two respective scenarios, making it completely reliable for its users. On top of that a semi-live training scenario was introduced, which helps improve the app performance over time as data accumulates. Overall, the problems of generalisability of complex models and data inefficiency is tackled through the model architecture. The app based setting with semi live training helps in ease of access to reliable healthcare in the society, as well as help ineffective research of rare diseases in a minimal data setting.

eess.IV↗