arXiv subjects

Roy George

Publications and source records attributed to Roy George.

17 recordsLinked to original sources

arXiv2026

TriCLE: Tri-Modal Vision-Language Reasoning for Edge-Deployed Fine-Grained Clustering

Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This setting is difficult for standard RGB-only recognition models and general-purpose vision-language models, especially when calibrated thermal and LiDAR aircraft data are unavailable. We present TriCLE, an application-oriented tri-modal vision-language system for aircraft taxonomic grouping under edge constraints. From a single RGB aircraft image, TriCLE generates a structure-preserving FLIR-style thermal view and a pseudo-LiDAR depth projection, then fuses the aligned views with task instructions in a compact Qwen3-VL backbone. The model is aligned to an expert aircraft taxonomy based on propulsion, airframe family, size, design era, and configuration, so its outputs reflect engineering-relevant similarity rather than only surface appearance. We evaluate supervised fine-tuning, rotation-preserving SFT, and three policy-alignment strategies: GRPO, GSPO, and DAPO. Sequence-level GSPO gives the strongest validation performance, reaching 88.33\% validation accuracy and 0.91 weighted F1 on valid aircraft outputs. On a held-out aircraft test partition, GSPO achieves 78.00\% accuracy and 0.793 weighted F1 while preserving 94.00\% parseable output formatting. After 4-bit quantization and attention-memory optimization, the aligned 4B model fits an 8GB deployment target and processes each tri-modal triplet in 1.48 seconds. These results support TriCLE as a practical prototype for interpretable, edge-feasible aircraft grouping, while emphasizing the need for further validation on real aligned thermal and LiDAR sensor streams.

cs.CV↗

arXiv2026

GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models

Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all change over time. Static bias benchmarks remain useful, but they do not show how models frame newly emerging events for different prompted audiences. We introduce GPF-LIVENEWS, a streaming evaluation protocol and benchmark snapshot for auditing group-conditioned framing in open-ended LLM outputs. The protocol expands fresh BBC/Reuters news anchors across 42 identity labels and seven prompt families, then evaluates response bundles using semantic-sensitivity and sentiment-disparity signals. In a pilot over 12 monitoring runs and 23 hosted models, Policy/Action prompts produce the strongest semantic movement, while sentiment variation is flatter across dimensions and prompt families. The released artifact includes article metadata, prompt templates, instantiated prompts, model-output metadata, score tables, documentation, and reproduction scripts. We interpret all scores as observed-window audit signals for human review, not as permanent fairness rankings or direct proof of harmful bias.

cs.CL↗

arXiv2026

LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception

Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficult because drones require low-latency closed-loop guidance under strict onboard compute and communication constraints. We present LiteVLA-H, a compact 256M-parameter VLA system designed for dual-rate operation on an NVIDIA Jetson AGX Orin: a fast outer-loop guidance mode for short action-token outputs and a slower semantic mode for scene understanding, hazard description, and operator-facing narration. The central empirical observation is that, in this compact edge regime, end-to-end latency is dominated by multimodal pre-fill rather than by the marginal cost of decoding a few extra tokens. This motivates a scheduler that issues reactive action tokens at 50.65,ms (19.74,Hz) while still supporting sentence-level semantic outputs at 149.90--164.57\ms (6.08--6.67,Hz) on the same embedded platform. To specialize the model without collapsing its descriptive competence, we use a knowledge-preserving fine-tuning recipe that mixes reactive flight data, aerial semantic data, and generic caption/VQA supervision. Beyond reporting current latency measurements, we position the system against recent state-of-the-art architectures, including AnywhereVLA, FutureVLA, and ReMem-VLA, showing that the measured action branch reaches a higher edge inference rate under our deployment conditions while retaining periodic semantic awareness.

cs.CV↗

arXiv2026

LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics

Vision-Language-Action (VLA) models provide a unified framework for perception, language conditioning, and action generation, but many existing systems remain difficult to deploy in embedded robotic settings because of their computational requirements and inference latency. In this paper, we present LiteVLA-Edge, a deployment-oriented VLA pipeline for fully on-device inference on Jetson Orin-class hardware. Our approach combines supervised image-to-action fine-tuning in FP32 with post-training 4-bit GGUF quantization and GPU-accelerated inference through the \texttt{llama.cpp} runtime. Under our deployment configuration, LiteVLA-Edge achieves a mean end-to-end latency of 150.5\,ms (approximately 6.6\,Hz) while operating entirely offline within a ROS~2-integrated perception--reasoning--action pipeline. Rather than introducing a new policy objective, our contribution is a practical systems path for executing compact multimodal control models locally on embedded hardware while preserving modular interfaces between perception, reasoning, and actuation. These results establish timing feasibility for reactive language-conditioned control and provide a reproducible baseline for future task-level evaluation of on-device VLAs in robotics.

cs.RO↗

arXiv2026

Verbatim Data Transcription Failures in LLM Code Generation: A State-Tracking Stress Test

Many real-world software tasks require exact transcription of provided data into code, such as cryptographic constants, protocol test vectors, allowlists, and calibration tables. These tasks are operationally sensitive because small omissions or alterations can remain silent while producing syntactically valid programs. This paper introduces a deliberately minimal transcription-to-code benchmark to isolate this reliability concern in LLM-based code generation. Given a list of high-precision decimal constants, a model must generate Python code that embeds the constants verbatim and performs a simple aggregate computation. We describe the prompting variants, evaluation protocol based on exact-string inclusion, and analysis framework used to characterize state-tracking and long-horizon generation failures. The benchmark is intended as a compact stress test that complements existing code-generation evaluations by focusing on data integrity rather than algorithmic reasoning.

cs.SE↗

arXiv2025

TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices

This paper investigates the effectiveness of small language models (SLMs) for agentic tasks (function/tool/API calling) with a focus on running agents on edge devices without reliance on cloud infrastructure. We evaluate SLMs using the Berkeley Function Calling Leaderboard (BFCL) framework and describe parameter-driven optimization strategies that include supervised fine-tuning (SFT), parameter-efficient fine-tuning (PEFT), reinforcement learning (RL)-based optimization, preference alignment via Direct Preference Optimization (DPO), and hybrid methods. We report results for models including TinyAgent, TinyLlama, Qwen, and xLAM across BFCL categories (simple, multiple, parallel, parallel-multiple, and relevance detection), both in live and non-live settings, and in multi-turn evaluations. We additionally detail a DPO training pipeline constructed from AgentBank data (e.g., ALFRED), including our conversion of SFT data to chosen-rejected pairs using TinyLlama responses as rejected outputs and manual validation. Our results demonstrate clear accuracy differences across model scales where medium-sized models (1-3B parameters) significantly outperform ultra-compact models (<1B parameters), achieving up to 65.74% overall accuracy, and 55.62% multi-turn accuracy with hybrid optimization. This study highlights the importance of hybrid optimization strategies that enable small language models to deliver accurate, efficient, and stable agentic AI on edge devices, making privacy-preserving, low-latency autonomous agents practical beyond the cloud.

cs.LG↗

arXiv2025

Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots

The deployment of artificial intelligence models at the edge is increasingly critical for autonomous robots operating in GPS-denied environments where local, resource-efficient reasoning is essential. This work demonstrates the feasibility of deploying small Vision-Language Models (VLMs) on mobile robots to achieve real-time scene understanding and reasoning under strict computational constraints. Unlike prior approaches that separate perception from mobility, the proposed framework enables simultaneous movement and reasoning in dynamic environments using only on-board hardware. The system integrates a compact VLM with multimodal perception to perform contextual interpretation directly on embedded hardware, eliminating reliance on cloud connectivity. Experimental validation highlights the balance between computational efficiency, task accuracy, and system responsiveness. Implementation on a mobile robot confirms one of the first successful deployments of small VLMs for concurrent reasoning and mobility at the edge. This work establishes a foundation for scalable, assured autonomy in applications such as service robotics, disaster response, and defense operations.

cs.RO↗

arXiv2025

VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment

General-purpose vision-language models (VLMs) such as LLaVA and QwenVL produce descriptions of disaster imagery that lack domain-specific vocabulary and actionable detail. We propose the Vision-Language Caption Enhancer (VLCE), a framework that integrates external semantic knowledge from ConceptNet and WordNet into the caption generation process for post-disaster satellite and UAV imagery. VLCE operates in two stages: first, a baseline VLM generates an initial caption conditioned on YOLOv8 object detections; second, a knowledge-enriched sequential model, a CNN-LSTM or a hierarchical cross-modal Transformer, refines the caption using a vocabulary augmented with 1,566 domain-relevant terms extracted from knowledge graphs. We evaluate VLCE on two disaster benchmarks: xBD (satellite, 6,369 images, 3 damage classes) and RescueNet (UAV, 4,494 images, 12 damage classes), using CLIPScore for semantic alignment and InfoMetIC for informativeness. On RescueNet with the Transformer decoder, VLCE with knowledge graph enrichment produces captions preferred over QwenVL baselines in 95.33% of image pairs on InfoMetIC and 73.64% on CLIPScore. Qualitative analysis shows that without knowledge graph integration, generated captions exhibit hallucinations, word repetition, and semantic incoherence, whereas knowledge-enriched captions maintain factual consistency and domain-appropriate vocabulary.

cs.CV↗

arXiv2025

Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules

Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many domains. We introduce the Domain Aware Rule Triggered Variational Autoencoder (DARTVAE), a rule guided multimodal clustering framework that incorporates domain specific constraints directly into the representation learning process. DARTVAE extends the VAE architecture by embedding explicit rules, semantic representations, and data driven features into a unified latent space, while enforcing constraint compliance through rule consistency and violation penalties in the loss function. Unlike conventional clustering methods that rely only on visual similarity or apply rules as post hoc filters, DARTVAE treats rules as first class learning signals. The rules are generated by LLMs, structured into knowledge graphs, and enforced through a loss function combining reconstruction, KL divergence, consistency, and violation penalties. Experiments on aircraft and automotive datasets demonstrate that rule guided clustering produces more operationally meaningful and interpretable clusters for example, isolating UAVs, unifying stealth aircraft, or separating SUVs from sedans while improving traditional clustering metrics. However, the framework faces challenges: LLM generated rules may hallucinate or conflict, excessive rules risk overfitting, and scaling to complex domains increases computational and consistency difficulties. By combining rule encodings with learned representations, DARTVAE achieves more meaningful and consistent clustering outcomes than purely data driven models, highlighting the utility of constraint guided multimodal clustering for complex, knowledge intensive settings.

cs.LG↗

arXiv2025

UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins

Cities today generate enormous streams of data from sensors, cameras, and connected infrastructure. While this information offers unprecedented opportunities to improve urban life, most existing systems struggle with scale, latency, and fragmented insights. This work introduces a framework that blends physics-informed machine learning, multimodal data fusion, and knowledge graph representation with adaptive, rule-based intelligence powered by large language models (LLMs). Physics-informed methods ground learning in real-world constraints, ensuring predictions remain meaningful and consistent with physical dynamics. Knowledge graphs act as the semantic backbone, integrating heterogeneous sensor data into a connected, queryable structure. At the edge, LLMs generate context-aware rules that adapt filtering and decision-making in real time, enabling efficient operation even under constrained resources. Together, these elements form a foundation for digital twin systems that go beyond passive monitoring to provide actionable insights. By uniting physics-based reasoning, semantic data fusion, and adaptive rule generation, this approach opens new possibilities for creating responsive, trustworthy, and sustainable smart infrastructures.

cs.AI↗

arXiv2025

Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM

The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts. To address this problem, we propose ATLASS, an advanced tool learning and selection system designed as a closed-loop framework. It enables the LLM to solve problems by dynamically generating external tools on demand. In this framework, agents play a crucial role in orchestrating tool selection, execution, and refinement, ensuring adaptive problem-solving capabilities. The operation of ATLASS follows three phases: The first phase, Understanding Tool Requirements, involves the Agents determining whether tools are required and specifying their functionality; the second phase, Tool Retrieval/Generation, involves the Agents retrieving or generating tools based on their availability; and the third phase, Task Solving, involves combining all the component tools necessary to complete the initial task. The Tool Dataset stores the generated tools, ensuring reusability and minimizing inference cost. Current LLM-based tool generation systems have difficulty creating complex tools that need APIs or external packages. In ATLASS, we solve the problem by automatically setting up the environment, fetching relevant API documentation online, and using a Python interpreter to create a reliable, versatile tool that works in a wider range of situations. OpenAI GPT-4.0 is used as the LLM agent, and safety and ethical concerns are handled through human feedback before executing generated code. By addressing the limitations of predefined toolsets and enhancing adaptability, ATLASS serves as a real-world solution that empowers users with dynamically generated tools for complex problem-solving.

cs.AI↗

arXiv2024

Physical Rule-Guided Convolutional Neural Network

The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neural Networks (PGNNs) have emerged to address these limitations by integrating scientific principles and real-world knowledge, enhancing model interpretability and efficiency. This paper proposes a novel Physics-Guided CNN (PGCNN) architecture that incorporates dynamic, trainable, and automated LLM-generated, widely recognized rules integrated into the model as custom layers to address challenges like limited data and low confidence scores. The PGCNN is evaluated on multiple datasets, demonstrating superior performance compared to a baseline CNN model. Key improvements include a significant reduction in false positives and enhanced confidence scores for true detection. The results highlight the potential of PGCNNs to improve CNN performance for broader application areas.

cs.CV↗

arXiv2024

Deep Learning for Automated Wound Classification And Segmentation

Wounds, such as foot ulcers, pressure ulcers, leg ulcers, and infected wounds, come up with substantial problems for healthcare professionals. Prompt and accurate segmentation is crucial for effective treatment. However, contemporary methods need an exhaustive model that is qualified for both classification and segmentation, especially lightweight ones. In this work, we tackle this issue by presenting a new architecture that incorporates U-Net, which is optimized for both wound classification and effective segmentation. We curated four extensive and diverse collections of wound images, utilizing the publicly available Medetec Dataset, and supplemented with additional data sourced from the Internet. Our model performed exceptionally well, with an F1 score of 0.929, a Dice score of 0.931 in segmentation, and an accuracy of 0.915 in classification, proving its effectiveness in both classification and segmentation work. This accomplishment highlights the potential of our approach to automating wound care management.

eess.IV↗

arXiv2024

Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks

Machine learning (ML) is a rapidly developing area of medicine that uses significant resources to apply computer science and statistics to medical issues. ML's proponents laud its capacity to handle vast, complicated, and erratic medical data. It's common knowledge that attackers might cause misclassification by deliberately creating inputs for machine learning classifiers. Research on adversarial examples has been extensively conducted in the field of computer vision applications. Healthcare systems are thought to be highly difficult because of the security and life-or-death considerations they include, and performance accuracy is very important. Recent arguments have suggested that adversarial attacks could be made against medical image analysis (MedIA) technologies because of the accompanying technology infrastructure and powerful financial incentives. Since the diagnosis will be the basis for important decisions, it is essential to assess how strong medical DNN tasks are against adversarial attacks. Simple adversarial attacks have been taken into account in several earlier studies. However, DNNs are susceptible to more risky and realistic attacks. The present paper covers recent proposed adversarial attack strategies against DNNs for medical imaging as well as countermeasures. In this study, we review current techniques for adversarial imaging attacks, detections. It also encompasses various facets of these techniques and offers suggestions for the robustness of neural networks to be improved in the future.

cs.CR↗

arXiv2024

AI-Driven Approaches for Optimizing Power Consumption: A Comprehensive Survey

Reduced environmental effect, lower operating costs, and a stable and sustainable energy supply for current and future generations are the main reasons why power optimization is important. Power optimization makes ensuring that energy is used more effectively, cutting down on waste and optimizing the utilization of resources.In today's world, power optimization and artificial intelligence (AI) integration are essential to changing the way energy is produced, used, and distributed. Real-time monitoring and analysis of power usage trends is made possible by AI-driven algorithms and predictive analytics, which enable dynamic modifications to effectively satisfy demand. Efficiency and sustainability are increased when power consumption is optimized in different sectors thanks to the use of intelligent systems. This survey paper comprises an extensive review of the several AI techniques used for power optimization as well as a methodical analysis of the literature for the study of various intelligent system application domains across different disciplines of power consumption.This literature review identifies the performance and outcomes of 17 different research methods by assessing them, and it aims to distill valuable insights into their strengths and limitations. Furthermore, this article outlines future directions in the integration of AI for power consumption optimization.

cs.AI↗

arXiv2024

Present and Future of AI in Renewable Energy Domain : A Comprehensive Survey

Artificial intelligence (AI) has become a crucial instrument for streamlining processes in various industries, including electrical power systems, as a result of recent digitalization. Algorithms for artificial intelligence are data-driven models that are based on statistical learning theory and are used as a tool to take use of the data that the power system and its users generate. Initially, we perform a thorough literature analysis of artificial intelligence (AI) applications related to renewable energy (RE). Next, we present a thorough analysis of renewable energy factories and assess their suitability, along with a list of the most widely used and appropriate AI algorithms. Nine AI-based strategies are identified here to assist Renewable Energy (RE) in contemporary power systems. This survey paper comprises an extensive review of the several AI techniques used for renewable energy as well as a methodical analysis of the literature for the study of various intelligent system application domains across different disciplines of renewable energy. This literature review identifies the performance and outcomes of nine different research methods by assessing them, and it aims to distill valuable insights into their strengths and limitations. This study also addressed three main topics: using AI technology for renewable power generation, utilizing AI for renewable energy forecasting, and optimizing energy systems. Additionally, it explored AI's superiority over conventional models in controllability, data handling, cyberattack prevention, smart grid implementation, robotics- AI's significance in shaping the future of the energy industry. Furthermore, this article outlines future directions in the integration of AI for renewable energy.

cs.LG↗

arXiv2014

Network Performance Rank: An Approach for Comparison of Complex Networks

Researchers have typically concentrated on analyzing what happens internally in a complex network and using this to distinguish between nodes. However, there has been less effort towards comparing between different networks. In this paper, we proposed a novel approach to rank alternative complex networks based on their performances. We consider this as a ranking problem in decision analysis based on occurring positive/negative frequent events as criteria, and using the TOPSIS method to rank alternatives. In order to assign a score to the networks for each criterion, a statistical method that estimates the expected value of positive/negative frequent events on a random node is presented. The proposed technique is efficient in terms of algorithm complexity and is capable of discriminating events occurring between important nodes over those between less significant nodes. The experiments, conducted on several synthetic networks, demonstrate the feasibility and applicability of the ranking methodology.

cs.SI↗