Showing 1–50 of 230 results for author: Ahmed, K

Unifying Graph Neural Networks Through a Common Layer Equation

Authors: Sai Karthik Navuluru, Siddhartha Shankar Das, Bo Ni, Hongjie Chen, Yu Wang, Baris Coskunuzer, Nesreen K. Ahmed, Franck Dernoncourt, Mahantesh Halappanavar, Tyler Derr, Ryan A. Rossi, Lakshman Tamil

Abstract: Graph neural networks are commonly described through family-specific equations whose notation obscures shared computations and structural differences. We introduce a common layer equation that represents covered architectures through seven components: an update domain, channel set, propagation bank, per-channel message maps, channel-fusion operator, ego/residual map, and update map. The central fa… ▽ More Graph neural networks are commonly described through family-specific equations whose notation obscures shared computations and structural differences. We introduce a common layer equation that represents covered architectures through seven components: an update domain, channel set, propagation bank, per-channel message maps, channel-fusion operator, ego/residual map, and update map. The central factorization separates where information moves, encoded by the propagation bank, from what moves, encoded by the message maps. Function-valued fillings extend the same equation across local message passing, attention, spectral filtering, global communication, relation-specific channels, higher-order domains, and geometric messages. We make this unification explicit and checkable through worked reductions of canonical layers and component assignments spanning seven nonexclusive architectural families. A fixed slot discipline assigns operations by computational role and defines the framework's coverage boundary. The decomposition also yields component-level theoretical insights: under endpoint-local messages and node-local updates, operator support bounds one-layer dependencies, and one-layer global mixing requires a full effective operator row under the stated hypotheses. The resulting framework organizes more than 200 architectures in a common design space, enables component-wise comparison and generation of structurally consistent architectures, and connects propagation choices to oversmoothing, oversquashing, heterophily, and expressivity. It further exposes the empirical inverse problem of mapping measurable graph and task properties to validated component choices. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Comments: 133 pages, including appendix; includes figures and tables

When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation

Authors: Muhammad Ashad Kabir, Kawsar Ahmed, Md. Osama

Abstract: Large language models (LLMs) have shown strong performance in text generation tasks, yet their effectiveness on headline generation remains sensitive to how input context is selected and presented. In this work, we investigate Bengali news headline generation as a document-level generation task that requires effective selection and presentation of salient contextual information from long-form arti… ▽ More Large language models (LLMs) have shown strong performance in text generation tasks, yet their effectiveness on headline generation remains sensitive to how input context is selected and presented. In this work, we investigate Bengali news headline generation as a document-level generation task that requires effective selection and presentation of salient contextual information from long-form articles. Using Gemini-2.0-Flash, Llama-3.3-70B, and GPT-4o, we systematically study the effects of context selection, prompting strategies, and in-context learning (i.e., few-shot) on the quality of headline generation. Our experiments show that providing the full article does not necessarily improve performance; instead, using selected lead paragraphs of the article can maintain, and in some cases improve, headline generation quality. We further compare Bengali Native Prompting (BNaP) and Cross-Lingual Prompting (XLP), and examine how each interacts with context-enriched prompt templates incorporating auxiliary contextual cues. Results demonstrate that prompting strategies substantially influence generation quality: XLP often yields stronger performance, particularly when combined with contextual enrichment, but its benefits are model-dependent. Additionally, few-shot prompting substantially improves Gemini, with most of the gain obtained from a single demonstration, whereas Llama shows limited benefit from additional examples. Overall, our findings highlight that effective Bengali news headline generation depends more on context relevance and prompt design than on increasing input length, offering practical insights for multilingual and low-resource LLM applications. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Comments: 11 pages

Personalized Auto-Research: Towards a True AI Co-Scientist

Authors: Bo Ni, Franck Dernoncourt, Hongjie Chen, Yu Wang, Nesreen K. Ahmed, Zhengzhong Tu, Tyler Derr, Ryan A. Rossi

Abstract: AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full papers are beginning to change how research is carried out. Despite this rapid progress, state-of-the-art systems remain researcher-agnostic: given a research goal, they optimize novelty, validity, or reviewer score while ignoring the individual scientist who will use the output. This… ▽ More AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full papers are beginning to change how research is carried out. Despite this rapid progress, state-of-the-art systems remain researcher-agnostic: given a research goal, they optimize novelty, validity, or reviewer score while ignoring the individual scientist who will use the output. This overlooks a fundamental fact about research, namely, that what counts as novel, valuable, or feasible depends on the researcher, including their prior work, methodological repertoire, and the collaborators and communities in which they are embedded. In this work, we introduce the problem of personalized auto-research, which conditions every stage of the research process on a representation of the individual researcher. We argue that personalization is not a convenience layer, but rather the fundamental property that allows an AI system to serve as a genuine co-scientist rather than a generic instrument. To address this problem, we propose a general and flexible framework that threads a graph-grounded researcher context through retrieval, hypothesis search, experimentation, writing, and review. The framework consists of three fundamental components: (i) graph-grounded researcher representations, (ii) personalization across the full research pipeline, and (iii) evaluation grounded in the individual. Notably, we highlight a one-size-fits-all failure mode where distinct researchers issuing the same goal receive essentially the same research, erasing the tacit knowledge through which novel ideas arise. Finally, we discuss fundamental open problems and challenges. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation

Authors: Quazi Ishtiaque Mahmud, Nesreen K. Ahmed, Ali Jannesari

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code. In this work,… ▽ More Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code. In this work, we propose CudaPerf, a reflective RL framework that incorporates both verifiable execution rewards and structural code-aware rewards derived from parallelization features (e.g., memory coalescing, occupancy, Arithmatic Intensity, and synchronization patterns). CudaPerf operates in two stages: (1) an offline pairwise ranking module that learns to distinguish strong and weak program candidates via contrastive comparisons, and (2) an online RL training phase that jointly optimizes for correctness, performance, and structural efficiency through a unified reward signal. To further enhance learning, CudaPerf utilizes iterative refinement using execution feedback enabling progressive improvement of generated candidates. We also introduce a dataset comprising 2.9k C to CUDA and 1k PyTorch to CUDA programs, each paired with diverse input configurations and multiple CUDA implementations encompassing diverse optimization strategies. CudaPerf is evaluated across multiple benchmarks comprising both C to CUDA and PyTorch to CUDA transformations. Empirical findings suggest that CudaPerf significantly outperforms strong baselines, including Qwen-3-32B (for C to CUDA) and CUDA Agent (for PyTorch to CUDA) by achieving up to 5X & 3.32X improvements in speedup, and 17% & 7% improvements in correctness, respectively. △ Less

Submitted 23 July, 2026; originally announced July 2026.

R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables

Authors: Maxwell Horton, Wei Lu, Quan Tran, Yury Astashonok, Kirmani Ahmed, Babak Damavandi, Anuj Kumar, Xiao Zhang, Seungwhan Moon

Abstract: Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmarks do not reflect the challenges of handling (1) natural egocentric video, (2) posed RGB-D video inputs, and (3) challenging quantitative 3D spatial reasoning Q&A. To fill this gap, we introduce R3D-Bench (Reasoning in 3D), a benchmark of 3,033 quanti… ▽ More Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmarks do not reflect the challenges of handling (1) natural egocentric video, (2) posed RGB-D video inputs, and (3) challenging quantitative 3D spatial reasoning Q&A. To fill this gap, we introduce R3D-Bench (Reasoning in 3D), a benchmark of 3,033 quantitative spatial reasoning questions across 15 types -- spanning multiple-choice, distance-based, and volumetric reasoning questions -- built on top of 57 egocentric video sequences from Aria Digital Twin. To set a strong baseline on this dataset, we introduce R3D, a model-agnostic spatial tool-calling framework. In contrast to existing approaches that directly embed 3D information into the model's input representation, R3D constructs a 3D scene from video using segmentation and depth-lifted object representations. It provides this information to an LLM through eight composable spatial tools. On R3D-Bench, R3D with Qwen3-VL 235B achieves 73.5% mean relative accuracy, substantially outperforming the best depth-enabled baseline (CuTR+Tools, 61.9%) and the best RGB-only baseline (Gemini 3 Flash, 46.5%). △ Less

Submitted 2 July, 2026; originally announced July 2026.

Decentralized Operations of Decarbonized Chemical Plants with Renewable-driven Transmission Systems

Authors: Richard Reed, Kazi Arman Ahmed, Saba Ghasemi, Zheyu Jiang, Paritosh Ramanan

Abstract: Electrification of ethane cracking offers a promising pathway to industrial decarbonization, provided that the electricity is sourced from renewable energy. However, integrating electrified chemical plant microgrids with a decarbonized power grid requires joint operations planning between Independent System Operators and chemical plants, which is hindered by the highly confidential nature of plant… ▽ More Electrification of ethane cracking offers a promising pathway to industrial decarbonization, provided that the electricity is sourced from renewable energy. However, integrating electrified chemical plant microgrids with a decarbonized power grid requires joint operations planning between Independent System Operators and chemical plants, which is hindered by the highly confidential nature of plant operational data. In this paper, we propose a privacy-friendly decentralized framework based on data isolation that jointly optimizes the Unit Commitment problem in the power system and microgrid scheduling in electrified ethane cracker plants. The framework employs the Alternating Direction Method of Multipliers, augmented with an auxiliary system-level penalty that accelerates convergence, allowing each subsystem to solve its local subproblem and share only minimal coordination signals. To reflect real-world conditions, numerical experiments are conducted on the ACTIVSg2000 test case, a synthetic model of the Texas transmission network, with 26 chemical plants identified from Texas mapped to their nearest grid connection points. In doing so, we characterize the cost of privacy-friendly decomposition on joint power and chemical system decisions, showing that data isolation results in consistently small optimality gaps, and that its emissions consequences are load-dependent and non-monotone. △ Less

Submitted 29 June, 2026; v1 submitted 22 June, 2026; originally announced June 2026.

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

Authors: Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli, Snigdha Ansu, Mohammadreza Teymoorianfard, Franck Dernoncourt, Hongjie Chen, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed

Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring. Existing approaches either evaluate complete trajectories in a single pass or partition them into independently scored windows, limiting their ability to connect evidence across temporally distant actions. We… ▽ More Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring. Existing approaches either evaluate complete trajectories in a single pass or partition them into independently scored windows, limiting their ability to connect evidence across temporally distant actions. We propose TRACE, a monitoring framework for long-horizon LLM agent trajectories. TRACE operates through a TIJ (Triage-Inspect-Judge) loop that identifies high-signal regions, performs targeted inspection while maintaining accumulated evidence across reasoning steps, and synthesizes a trajectory-level verdict. We evaluate TRACE on ten task domains from SHADE-Arena against state-of-the-art baselines. TRACE achieves an aggregate F1 of 0.713 and recall of 0.844, with the largest gains on tasks requiring long-range evidence linking. △ Less

Submitted 5 June, 2026; originally announced June 2026.

XOR Bidding and Knapsack Formulations for HPC Network Resource Allocation

Authors: Abrar Hossain, Kishwar Ahmed

Abstract: Modern High Performance Computing (HPC) centers face growing challenges in ingesting large and diverse data streams. These issues often create bottlenecks that limit bandwidth utilization and delay scientific progress. Traditional static allocation and simple queuing methods are often insufficient. This paper presents a dynamic, value-based approach to bandwidth allocation. We formalize the proble… ▽ More Modern High Performance Computing (HPC) centers face growing challenges in ingesting large and diverse data streams. These issues often create bottlenecks that limit bandwidth utilization and delay scientific progress. Traditional static allocation and simple queuing methods are often insufficient. This paper presents a dynamic, value-based approach to bandwidth allocation. We formalize the problem by incorporating both network and processing constraints. To address it, we introduce two auction-based mechanisms: the Greedy Value Density Auction, which is computationally efficient, and the Vickrey--Clarke--Groves (VCG) Knapsack Auction, which provides strong theoretical guarantees. Both mechanisms rely on user bids that specify data requirements and scientific value. The objective is to maximize the total value of successful transfers, commonly referred to as social welfare. Simulation results demonstrate that the proposed mechanisms significantly outperform First Come First Served (FCFS) baselines. Under high-load conditions, they reduce average and tail completion delays by more than 80%. Predictability also improves, with the coefficient of variation of delay decreasing by 75--85%. Network stability increases as well, with load volatility, measured by the peak-to-average ratio, decreasing by 60--70%. These results indicate that value-driven, adaptive bandwidth allocation can reduce congestion, improve resource utilization, and provide fairer access based on scientific importance. △ Less

Submitted 29 May, 2026; originally announced June 2026.

Journal ref: Platform for Advanced Scientific Computing Conference (PASC 2026)

Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning

Authors: Nesreen K. Ahmed, Nima Nafisi

Abstract: Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially benign behavior, making detection difficult even with full trajectory access. Prior monitoring approaches improve scaffolding or ensemble aggregation, but treat e… ▽ More Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially benign behavior, making detection difficult even with full trajectory access. Prior monitoring approaches improve scaffolding or ensemble aggregation, but treat each trajectory independently and do not learn from prior monitoring experience. Moreover, standard reasoning methods explain observed behavior without explicitly reasoning about agent beliefs, intentions, and goal alignment required to distinguish benign task execution from covert deviation. We propose \textbf{Agent-ToM}, a learning-to-monitor framework grounded in Theory-of-Mind (ToM) reasoning for security analysis of autonomous agents. Agent-ToM performs structured full-trajectory analysis by inferring beliefs, intent hypotheses with calibrated confidence, expected actions, and deviations from task-consistent behavioral baselines. At inference time, it employs a \textit{Reason-Verify-Refine} pipeline to construct and validate monitoring decisions. At training time, Agent-ToM distills critique signals into a persistent \textit{semantic guardrail memory}, enabling reusable belief- and intent-conditioned constraints across episodes. We evaluate Agent-ToM on adversarial agent monitoring benchmarks (SHADE-Arena and CUA-SHADE-Arena). Agent-ToM achieves strong precision-recall balance and outperforms state-of-the-art monitoring baselines, including ensemble methods, while using a coherent two-call reasoning pipeline. These results demonstrate that learning at the monitoring layer, combined with structured ToM reasoning and verification, provides an effective and deployable foundation for securing autonomous LLM agents. △ Less

Submitted 22 May, 2026; originally announced May 2026.

Comments: 23 pages, 9 figures

DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion

Authors: Khaled Ahmed, Ghada Omar

Abstract: DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data. Moving away from traditional subsurface discretization, the framework regresses four earth-model parameters -- $σ_1$, $σ_2$, $d_1$, $d_2$ -- and reconstructs conductivity-depth profiles using a differentiable soft-step decoder. The optimized architecture (379K par… ▽ More DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data. Moving away from traditional subsurface discretization, the framework regresses four earth-model parameters -- $σ_1$, $σ_2$, $d_1$, $d_2$ -- and reconstructs conductivity-depth profiles using a differentiable soft-step decoder. The optimized architecture (379K parameters) features a Temporal Convolutional Network (TCN) encoder paired with a late-time branch and an auxiliary seafloor-depth head. This design achieves a 25.3\% loss reduction over baseline models, with high predictive accuracy ($R^2 = 0.898$ for $σ_2$) and an inversion speed of 3.5~ms per sample on an A100 GPU. The framework demonstrates high robustness to noise through curriculum-based amplitude augmentation, maintaining a mean $\bar{R}^2$ of 0.858 at $\pm2\%$ random amplitude error, compared to $0.363$ without augmentation. DualTCN generalizes effectively to three-layer extensions (seawater/resistive layer/basement), accurately resolving basement conductivity ($R^2 \approx 0.88$), though thin-layer resolution remains a physical limitation ($R^2 \approx 0.23$). In comparative benchmarks, DualTCN significantly outperforms traditional local optimization methods like Levenberg-Marquardt and L-BFGS-B, yielding a mean $\bar{R}^2 = 0.877$ versus 0.129-0.439 for multi-start baselines, while operating at up to 21,000$\times$ lower computational cost. Finally, the framework incorporates uncertainty quantification via Monte Carlo (MC) Dropout. While well-calibrated for $σ_1$ (PICP90 = 0.944), inherent signal limitations at short offsets (200m) lead to under-coverage for $d_2$ (PICP90 = 0.572), which can be mitigated through post-hoc temperature scaling or split conformal prediction. △ Less

Submitted 6 May, 2026; originally announced May 2026.

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

Authors: Hanane Nour Moussa, Yifei Li, Zhuoyang Li, Yankai Yang, Cheng Tang, Tianshu Zhang, Nesreen K. Ahmed, Ali Payani, Ziru Chen, Huan Sun

Abstract: Despite recent progress in language models and agents for scientific data-driven discovery, further advancing their capabilities is held back by the absence of verifiable environments representing real-world scientific tasks. To fill this gap, we introduce D3-Gym, the first automatically constructed dataset with verifiable environments for scientific Data-Driven Discovery. D3-Gym comprises (1) 565… ▽ More Despite recent progress in language models and agents for scientific data-driven discovery, further advancing their capabilities is held back by the absence of verifiable environments representing real-world scientific tasks. To fill this gap, we introduce D3-Gym, the first automatically constructed dataset with verifiable environments for scientific Data-Driven Discovery. D3-Gym comprises (1) 565 tasks sourced from 239 real scientific repositories across four disciplines where (2) each task is equipped with a natural language instruction, an executable environment with pre-installed dependencies, input dataset and artifact previews, a reference code solution, and an automatically synthesized evaluation script. Rigorous evaluation of the quality of the verification signal in D3-Gym confirms that our evaluation scripts achieve 87.5% agreement with human-annotated gold standards and strong alignment in domain-specific evaluation logic, showing their scientific soundness. Further, training on trajectories sampled from D3-Gym yields consistent and substantial gains across Qwen3 models of varying sizes on ScienceAgentBench, boosting Qwen3-32B by 7.8 absolute points and substantially shrinking the gap with strong proprietary models. All D3-Gym artifacts (environments, creation workflow, trajectories, and models) can be found at https://github.com/OSU-NLP-Group/D3-Gym. △ Less

Submitted 1 May, 2026; v1 submitted 30 April, 2026; originally announced April 2026.

Sparse Personalized Text Generation with Multi-Trajectory Reasoning

Authors: Bo Ni, Haowei Fu, Qinwen Ge, Franck Dernoncourt, Samyadeep Basu, Nedim Lipka, Seunghyun Yoon, Yu Wang, Nesreen K. Ahmed, Subhojyoti Mukherjee, Puneet Mathur, Ryan A. Rossi, Tyler Derr

Abstract: As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on dense interaction histories, making them ineffective in cold-start scenarios where such data is sparse or unavailable. While external signals (e.g., content of similar users) can offer a potential remedy, leveraging them… ▽ More As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on dense interaction histories, making them ineffective in cold-start scenarios where such data is sparse or unavailable. While external signals (e.g., content of similar users) can offer a potential remedy, leveraging them effectively remains challenging: raw context is often noisy, and existing methods struggle to reason over heterogeneous data sources. To address these issues, we introduce PAT (Personalization with Aligned Trajectories), a reasoning framework for cold-start LLM personalization. PAT first retrieves information along two complementary trajectories: writing-style cues from stylistically similar users and topic-specific context from preference-aligned users. It then employs a reinforcement learning-based, iterative dual-reasoning mechanism that enables the LLM to jointly refine and integrate these signals. Experimental results across real-world personalization benchmarks show that PAT consistently improves generation quality and alignment under sparse-data conditions, establishing a strong solution to the cold-start personalization problem. △ Less

Submitted 27 April, 2026; originally announced April 2026.

FryNet: Dual-Stream Adversarial Fusion for Non-Destructive Frying Oil Oxidation Assessment

Authors: Khaled R Ahmed, Toqi Tahamid Sarker, Taminul Islam, Tamany M Alanezi, Amer AbuGhazaleh

Abstract: Monitoring frying oil degradation is critical for food safety, yet current practice relies on destructive wet-chemistry assays that provide no spatial information and are unsuitable for real-time use. We identify a fundamental obstacle in thermal-image-based inspection, the camera-fingerprint shortcut, whereby models memorize sensor-specific noise and thermal bias instead of learning oxidation che… ▽ More Monitoring frying oil degradation is critical for food safety, yet current practice relies on destructive wet-chemistry assays that provide no spatial information and are unsuitable for real-time use. We identify a fundamental obstacle in thermal-image-based inspection, the camera-fingerprint shortcut, whereby models memorize sensor-specific noise and thermal bias instead of learning oxidation chemistry, collapsing under video-disjoint evaluation. We propose FryNet, a dual-stream RGB-thermal framework that jointly performs oil-region segmentation, serviceability classification, and regression of four chemical oxidation indices (PV, p-AV, Totox, temperature) in a single forward pass. A ThermalMiT-B2 backbone with channel and spatial attention extracts thermal features, while an RGB-MAE Encoder learns chemically grounded representations via masked autoencoding and chemical alignment. Dual-Encoder DANN adversarially regularizes both streams against video identity via Gradient Reversal Layers, and FiLM fusion bridges thermal structure with RGB chemical context. On 7,226 paired frames across 28 frying videos, FryNet achieves 98.97% mIoU, 100% classification accuracy, and 2.32 mean regression MAE, outperforming all seven baselines. △ Less

Submitted 23 April, 2026; originally announced April 2026.

Comments: 10 pages, 7 figures, this paper has been submitted and accepted for publication at CVPRW 2026

Synthetic Data in Education: Empirical Insights from Traditional Resampling and Deep Generative Models

Authors: Tapiwa Amion Chinodakufa, Ashfaq Ali Shafin, Khandaker Mamun Ahmed

Abstract: Synthetic data generation offers promise for addressing data scarcity and privacy concerns in educational technology, yet practitioners lack empirical guidance for selecting between traditional resampling techniques and modern deep learning approaches. This study presents the first systematic benchmark comparing these paradigms using a 10,000-record student performance dataset. We evaluate three r… ▽ More Synthetic data generation offers promise for addressing data scarcity and privacy concerns in educational technology, yet practitioners lack empirical guidance for selecting between traditional resampling techniques and modern deep learning approaches. This study presents the first systematic benchmark comparing these paradigms using a 10,000-record student performance dataset. We evaluate three resampling methods (SMOTE, Bootstrap, Random Oversampling) against three deep learning models (Autoencoder, Variational Autoencoder, Copula-GAN) across multiple dimensions: distributional fidelity (Kolmogorov-Smirnov distance, Jensen-Shannon divergence), machine learning utility such as Train-on-Synthetic-Test-on-Real scores (TSTR), and privacy preservation (Distance to Closest Record). Our findings reveal a fundamental trade-off: resampling methods achieve near-perfect utility (TSTR: 0.997) but completely fail privacy protection (DCR ~ 0.00), while deep learning models provide strong privacy guarantees (DCR ~ 1.00) at significant utility cost. Variational Autoencoders emerge as the optimal compromise, maintaining 83.3% predictive performance while ensuring complete privacy protection. We also provide actionable recommendations: use traditional resampling for internal development where privacy is controlled, and VAEs for external data sharing where privacy is paramount. This work establishes a foundational benchmark and practical decision framework for synthetic data generation in learning analytics. △ Less

Submitted 22 April, 2026; originally announced April 2026.

Journal ref: The 40th Annual AAAI Conference on Artificial Intelligence: AI4EDU, 2026

TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock

Authors: Taminul Islam, Abdellah Lakhssassi, Toqi Tahamid Sarker, Mohamed Embaby, Khaled R Ahmed, Amer AbuGhazaleh

Abstract: Quantifying exhaled CO2 from free-roaming cattle is both a direct indicator of rumen metabolic state and a prerequisite for farm-scale carbon accounting, yet no existing system can deliver continuous, spatially resolved measurements without physical confinement or contact. We present TRACE (Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock), the first unified framework to jo… ▽ More Quantifying exhaled CO2 from free-roaming cattle is both a direct indicator of rumen metabolic state and a prerequisite for farm-scale carbon accounting, yet no existing system can deliver continuous, spatially resolved measurements without physical confinement or contact. We present TRACE (Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock), the first unified framework to jointly address per-frame CO2 plume segmentation and clip-level emission flux classification from mid-wave infrared (MWIR) thermal video. TRACE contributes three domain-specific advances: a Thermal Gas-Aware Attention (TGAA) encoder that incorporates per-pixel gas intensity as a spatial supervisory signal to direct self-attention toward high-emission regions at each encoder stage; an Attention-based Temporal Fusion (ATF) module that captures breath-cycle dynamics through structured cross-frame attention for sequence-level flux classification; and a four-stage progressive training curriculum that couples both objectives while preventing gradient interference. Benchmarked against fifteen state-of-the-art models on the CO2 Farm Thermal Gas Dataset, TRACE achieves an mIoU of 0.998 and the best result on every segmentation and classification metric simultaneously, outperforming domain-specific gas segmenters with several times more parameters and surpassing all baselines in flux classification. Ablation studies confirm that each component is individually essential: gas-conditioned attention alone determines precise plume boundary localization, and temporal reasoning is indispensable for flux-level discrimination. TRACE establishes a practical path toward non-invasive, continuous, per-animal CO2 monitoring from overhead thermal cameras at commercial scale. Codes are available at https://github.com/taminulislam/trace. △ Less

Submitted 27 March, 2026; originally announced April 2026.

From Pixels to Semantics: A Multi-Stage AI Framework for Structural Damage Detection in Satellite Imagery

Authors: Bijay Shakya, Catherine Hoier, Khandaker Mamun Ahmed

Abstract: Rapid and accurate structural damage assessment following natural disasters is critical for effective emergency response and recovery. However, remote sensing imagery often suffers from low spatial resolution, contextual ambiguity, and limited semantic interpretability, reducing the reliability of traditional detection pipelines. In this work, we propose a novel hybrid framework that integrates AI… ▽ More Rapid and accurate structural damage assessment following natural disasters is critical for effective emergency response and recovery. However, remote sensing imagery often suffers from low spatial resolution, contextual ambiguity, and limited semantic interpretability, reducing the reliability of traditional detection pipelines. In this work, we propose a novel hybrid framework that integrates AI-based super-resolution, deep learning object detection, and Vision-Language Models (VLMs) for comprehensive post-disaster building damage assessment. First, we enhance pre- and post-disaster satellite imagery using a Video Restoration Transformer (VRT) to upscale images from 1024x1024 to 4096x4096 resolution, improving structural detail visibility. Next, a YOLOv11-based detector localizes buildings in pre-disaster imagery, and cropped building regions are analyzed using VLMs to semantically assess structural damage across four severity levels. To ensure robust evaluation in the absence of ground-truth captions, we employ CLIPScore for reference-free semantic alignment and introduce a multi-model VLM-as-a-Jury strategy to reduce individual model bias in safety-critical decision making. Experiments on subsets of the xBD dataset, including the Moore Tornado and Hurricane Matthew events, demonstrate that the proposed framework enhances the semantic interpretation of damaged buildings. In addition, our framework provides helpful recommendations to first responders for recovery based on damage analysis. △ Less

Submitted 23 March, 2026; originally announced March 2026.

Journal ref: IEEE/CVF Conference on Computer Vision & Pattern Recognition Workshop (CVPRW) 2026

A Hybrid AI and Rule-Based Decision Support System for Disease Diagnosis and Management Using Labs

Authors: Muhammad Hammad Maqsood, Mubashir Sajid, Khubaib Ahmed, Muhammad Usamah Shahid, Muddassar Farooq

Abstract: This research paper outlines the development and implementation of a novel Clinical Decision Support System (CDSS) that integrates AI predictive modeling with medical knowledge bases. It utilizes the quantifiable information elements in lab results for inferring likely diagnoses a patient might have. Subsequently, suggesting investigations to confirm the likely diagnoses -- an assistive tool for p… ▽ More This research paper outlines the development and implementation of a novel Clinical Decision Support System (CDSS) that integrates AI predictive modeling with medical knowledge bases. It utilizes the quantifiable information elements in lab results for inferring likely diagnoses a patient might have. Subsequently, suggesting investigations to confirm the likely diagnoses -- an assistive tool for physicians. The system fuses knowledge contained in a rule-base expert system with inferences of data driven predictors based on the features in labs. The data for 593,055 patients was collected from 547 primary care centers across the US to model our decision support system and derive Real-Word Evidence (RWE) to make it relevant for a large demographic of patients. Our Rule-Base comprises clinically validated rules, modeling 59 health conditions that can directly confirm one or more of diseases and assign ICD-10 codes to them. The Likely Diagnosis system uses multi-class classification, covering 37 ICD-10 codes, which are grouped together into 11 categories based on the labs that physicians prescribe to confirm the diagnosis. This research offers a novel system that assists a physician by utilizing medical profile of a patient and routine lab investigations to predict a group of likely diseases and then confirm them, coupled with providing explanations for inferences, thereby assisting physicians to reduce misdiagnosis of patients in clinical decision-making. △ Less

Submitted 16 March, 2026; originally announced March 2026.

Radiation-induced segregation in dilute Fe-Cr: A rate-theory framework for the Cr enrichment-depletion transition at the grain boundary

Authors: Russell Oplinger, Mukesh Bachhav, Karim Ahmed, Sourabh Bhagwan Kadambi

Abstract: Radiation-induced segregation (RIS) poses a significant challenge for ferritic Fe-Cr alloys under irradiation, as it can compromise mechanical integrity and increase susceptibility to intergranular corrosion. Yet, the mechanisms governing Cr segregation remain incompletely understood. In this study, We present a physics-based rate-theory model parameterized using self-consistent mean field theory-… ▽ More Radiation-induced segregation (RIS) poses a significant challenge for ferritic Fe-Cr alloys under irradiation, as it can compromise mechanical integrity and increase susceptibility to intergranular corrosion. Yet, the mechanisms governing Cr segregation remain incompletely understood. In this study, We present a physics-based rate-theory model parameterized using self-consistent mean field theory-based Onsager transport coefficients to investigate RIS at the grain boundary (GB) in dilute Fe-(0.1 at.%) Cr. Under equal production rates of vacancies and self-interstitial atoms (SIA), and their equal absorption rates by bulk dislocations, the model simulates the experimentally observed transition from Cr enrichment at low temperatures to depletion at higher temperatures. Under these unbiased conditions, systematic investigation reveals that while temperature-dependent transport properties dictate the segregation direction, dose rate, grain size, and dislocation density only influence the magnitude and spatial extent of Cr segregation. However, under more realistic conditions of preferential vacancy production within damage cascade and/or preferential SIA absorption by bulk dislocations, the enrichment-to-depletion transition shifts to lower temperatures. Our findings demonstrate that RIS predictions based solely on transport coefficients are valid only under symmetric point defect flux conditions, and that biases in defect production and absorption must be considered for accurate predictions. This work provides a mechanistic framework for understanding RIS in ferritic alloys and informs alloy design for advanced nuclear systems. △ Less

Submitted 15 March, 2026; originally announced March 2026.

Design Framework and Manufacturing of an Active Magnetic Bearing Spindle for Micro-Milling Applications

Authors: Kazi Sher Ahmed, Bekir Bediz

Abstract: Micro-milling spindles require high rotational speeds where conventional rolling element bearings face limitations such as friction and thermal expansion. Active magnetic bearings (AMBs) address these challenges by providing non-contact and lubrication-free operation at ultra-high speeds with the ability to actively regulate spindle dynamics. The existing literature on AMB spindles has mainly repo… ▽ More Micro-milling spindles require high rotational speeds where conventional rolling element bearings face limitations such as friction and thermal expansion. Active magnetic bearings (AMBs) address these challenges by providing non-contact and lubrication-free operation at ultra-high speeds with the ability to actively regulate spindle dynamics. The existing literature on AMB spindles has mainly reported specific prototype realizations or control system implementations for specific spindle dynamics. Consequently, design knowledge remains fragmented across isolated successful studies. This paper addresses this gap by presenting a systematic and iterative framework to design and manufacture a micro-milling AMB spindle. The process involves a multidisciplinary design flow with a focus on critical practical aspects of manufacturing. The realized spindle is reported as a case study. △ Less

Submitted 3 March, 2026; v1 submitted 26 February, 2026; originally announced March 2026.

Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis

Authors: Runzhou Liu, Hailey Weingord, Sejal Mittal, Prakhar Dungarwal, Anusha Nandula, Bo Ni, Samyadeep Basu, Hongjie Chen, Nesreen K. Ahmed, Li Li, Jiayi Zhang, Koustava Goswami, Subhojyoti Mukherjee, Branislav Kveton, Puneet Mathur, Franck Dernoncourt, Yue Zhao, Yu Wang, Ryan A. Rossi, Zhengzhong Tu, Hongru Du

Abstract: Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important to human perception and intent. Such metrics frequently reward visually plausible outputs while overlooking controllability, edit localization, and faithfulness to user instructions. In this work, we introduce a fine-gr… ▽ More Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important to human perception and intent. Such metrics frequently reward visually plausible outputs while overlooking controllability, edit localization, and faithfulness to user instructions. In this work, we introduce a fine-grained Multimodal Large Language Model (MLLM)-as-a-Judge framework for image editing that decomposes common evaluation notions into twelve fine-grained interpretable factors spanning image preservation, edit quality, and instruction fidelity. Building on this formulation, we present a new human-validated benchmark that integrates human judgments, MLLM-based evaluations, model outputs, and traditional metrics across diverse image editing tasks. Through extensive human studies, we show that the proposed MLLM judges align closely with human evaluations at a fine granularity, supporting their use as reliable and scalable evaluators. We further demonstrate that traditional image editing metrics are often poor proxies for these factors, failing to distinguish over-edited or semantically imprecise outputs, whereas our judges provide more intuitive and informative assessments in both offline and online settings. Together, this work introduces a benchmark, a principled factorization, and empirical evidence positioning fine-grained MLLM judges as a practical foundation for studying, comparing, and improving image editing approaches. △ Less

Submitted 13 February, 2026; originally announced February 2026.

OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization

Authors: Arijit Bhattacharjee, Heng Ping, Son Vu Le, Paul Bogdan, Nesreen K. Ahmed, Ali Jannesari

Abstract: Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize functionally correct CUDA code, achieving competitive performance requires systematic exploration and verification of optimization choices. We present OptiML, an end-to-… ▽ More Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize functionally correct CUDA code, achieving competitive performance requires systematic exploration and verification of optimization choices. We present OptiML, an end-to-end framework that maps either natural-language intent or input CUDA code to performance-optimized CUDA kernels by formulating kernel optimization as search under verification. OptiML consists of two decoupled stages. When the input is natural language, a Mixture-of-Thoughts generator (OptiML-G) acts as a proposal policy over kernel implementation strategies, producing an initial executable program. A search-based optimizer (OptiML-X) then refines either synthesized or user-provided kernels using Monte Carlo Tree Search over LLM-driven edits, guided by a hardware-aware reward derived from profiler feedback. Each candidate transformation is compiled, verified, and profiled with Nsight Compute, and evaluated by a composite objective that combines runtime with hardware bottleneck proxies and guardrails against regressions. We evaluate OptiML in both synthesis-and-optimize and optimization-only settings on a diverse suite of CUDA kernels. Results show that OptiML consistently discovers verified performance improvements over strong LLM baselines and produces interpretable optimization trajectories grounded in profiler evidence. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Blind to the Human Touch: Overlap Bias in LLM-Based Summary Evaluation

Authors: Jiangnan Fang, Cheng-Tse Liu, Hanieh Deilamsalehy, Nesreen K. Ahmed, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi

Abstract: Large language model (LLM) judges have often been used alongside traditional, algorithm-based metrics for tasks like summarization because they better capture semantic information, are better at reasoning, and are more robust to paraphrasing. However, LLM judges show biases for length and order among others, and are vulnerable to various adversarial input prompts. While recent studies have looked… ▽ More Large language model (LLM) judges have often been used alongside traditional, algorithm-based metrics for tasks like summarization because they better capture semantic information, are better at reasoning, and are more robust to paraphrasing. However, LLM judges show biases for length and order among others, and are vulnerable to various adversarial input prompts. While recent studies have looked into these biases, few have analyzed them at a more granular level in relation to a well-defined overlap metric. In this work we provide an LLM judge bias analysis as a function of overlap with human-written responses in the domain of summarization. We test 9 recent LLMs with parameter counts ranging from 1 billion to 12 billion, including variants of Gemma 3 and LLaMA 3. We find that LLM judges increasingly prefer summaries generated by other LLMs over those written by humans as the similarities (as measured by ROUGE and BLEU) between the judged summaries decrease, and this pattern extends to all but one model tested, and exists regardless of the models' own position biases. Additionally, we find that models struggle to judge even summaries with limited overlaps, suggesting that LLM-as-a-judge in the summary domain should rely on techniques beyond a simple comparison. △ Less

Submitted 7 February, 2026; originally announced February 2026.

Segment Length Matters: A Study of Segment Lengths on Audio Fingerprinting Performance

Authors: Ziling Gong, Yunyan Ouyang, Iram Kamdar, Melody Ma, Hongjie Chen, Franck Dernoncourt, Ryan A. Rossi, Nesreen K. Ahmed

Abstract: Audio fingerprinting provides an identifiable representation of acoustic signals, which can be later used for identification and retrieval systems. To obtain a discriminative representation, the input audio is usually segmented into shorter time intervals, allowing local acoustic features to be extracted and analyzed. Modern neural approaches typically operate on short, fixed-duration audio segmen… ▽ More Audio fingerprinting provides an identifiable representation of acoustic signals, which can be later used for identification and retrieval systems. To obtain a discriminative representation, the input audio is usually segmented into shorter time intervals, allowing local acoustic features to be extracted and analyzed. Modern neural approaches typically operate on short, fixed-duration audio segments, yet the choice of segment duration is often made heuristically and rarely examined in depth. In this paper, we study how segment length affects audio fingerprinting performance. We extend an existing neural fingerprinting architecture to adopt various segment lengths and evaluate retrieval accuracy across different segment lengths and query durations. Our results show that short segment lengths (0.5-second) generally achieve better performance. Moreover, we evaluate LLM capacity in recommending the best segment length, which shows that GPT-5-mini consistently gives the best suggestions across five considerations among three studied LLMs. Our findings provide practical guidance for selecting segment duration in large-scale neural audio retrieval systems. △ Less

Submitted 24 January, 2026; originally announced January 2026.

Introducing Axlerod: An LLM-based Chatbot for Assisting Independent Insurance Agents

Authors: Adam Bradley, John Hastings, Khandaker Mamun Ahmed

Abstract: The insurance industry is undergoing a paradigm shift through the adoption of artificial intelligence (AI) technologies, particularly in the realm of intelligent conversational agents. Chatbots have evolved into sophisticated AI-driven systems capable of automating complex workflows, including policy recommendation and claims triage, while simultaneously enabling dynamic, context-aware user engage… ▽ More The insurance industry is undergoing a paradigm shift through the adoption of artificial intelligence (AI) technologies, particularly in the realm of intelligent conversational agents. Chatbots have evolved into sophisticated AI-driven systems capable of automating complex workflows, including policy recommendation and claims triage, while simultaneously enabling dynamic, context-aware user engagement. This paper presents the design, implementation, and empirical evaluation of Axlerod, an AI-powered conversational interface designed to improve the operational efficiency of independent insurance agents. Leveraging natural language processing (NLP), retrieval-augmented generation (RAG), and domain-specific knowledge integration, Axlerod demonstrates robust capabilities in parsing user intent, accessing structured policy databases, and delivering real-time, contextually relevant responses. Experimental results underscore Axlerod's effectiveness, achieving an overall accuracy of 93.18% in policy retrieval tasks while reducing the average search time by 2.42 seconds. This work contributes to the growing body of research on enterprise-grade AI applications in insurtech, with a particular focus on agent-assistive rather than consumer-facing architectures. △ Less

Submitted 24 December, 2025; originally announced January 2026.

Comments: 6 pages, 2 figures, 1 table

ACM Class: I.2.7; H.3.3; H.5.2

Journal ref: 2025 IEEE Cyber Awareness and Research Symposium (CARS'25)

FUME: Fused Unified Multi-Gas Emission Network for Livestock Rumen Acidosis Detection

Authors: Taminul Islam, Toqi Tahamid Sarker, Mohamed Embaby, Khaled R Ahmed, Amer AbuGhazaleh

Abstract: Ruminal acidosis is a prevalent metabolic disorder in dairy cattle causing significant economic losses and animal welfare concerns. Current diagnostic methods rely on invasive pH measurement, limiting scalability for continuous monitoring. We present FUME (Fused Unified Multi-gas Emission Network), the first deep learning approach for rumen acidosis detection from dual-gas optical imaging under in… ▽ More Ruminal acidosis is a prevalent metabolic disorder in dairy cattle causing significant economic losses and animal welfare concerns. Current diagnostic methods rely on invasive pH measurement, limiting scalability for continuous monitoring. We present FUME (Fused Unified Multi-gas Emission Network), the first deep learning approach for rumen acidosis detection from dual-gas optical imaging under in vitro conditions. Our method leverages complementary carbon dioxide (CO2) and methane (CH4) emission patterns captured by infrared cameras to classify rumen health into Healthy, Transitional, and Acidotic states. FUME employs a lightweight dual-stream architecture with weight-shared encoders, modality-specific self-attention, and channel attention fusion, jointly optimizing gas plume segmentation and classification of dairy cattle health. We introduce the first dual-gas OGI dataset comprising 8,967 annotated frames across six pH levels with pixel-level segmentation masks. Experiments demonstrate that FUME achieves 80.99% mIoU and 98.82% classification accuracy while using only 1.28M parameters and 1.97G MACs--outperforming state-of-the-art methods in segmentation quality with 10x lower computational cost. Ablation studies reveal that CO2 provides the primary discriminative signal and dual-task learning is essential for optimal performance. Our work establishes the feasibility of gas emission-based livestock health monitoring, paving the way for practical, in vitro acidosis detection systems. Codes are available at https://github.com/taminulislam/fume. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Comments: 10 pages, 5 figures

Journal ref: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2026, pp. 510-519

WeedRepFormer: Reparameterizable Vision Transformers for Real-Time Waterhemp Segmentation and Gender Classification

Authors: Toqi Tahamid Sarker, Taminul Islam, Khaled R. Ahmed, Cristiana Bernardi Rankrape, Kaitlin E. Creager, Karla Gage

Abstract: We present WeedRepFormer, a lightweight multi-task Vision Transformer designed for simultaneous waterhemp segmentation and gender classification. Existing agricultural models often struggle to balance the fine-grained feature extraction required for biological attribute classification with the efficiency needed for real-time deployment. To address this, WeedRepFormer systematically integrates stru… ▽ More We present WeedRepFormer, a lightweight multi-task Vision Transformer designed for simultaneous waterhemp segmentation and gender classification. Existing agricultural models often struggle to balance the fine-grained feature extraction required for biological attribute classification with the efficiency needed for real-time deployment. To address this, WeedRepFormer systematically integrates structural reparameterization across the entire architecture - comprising a Vision Transformer backbone, a Lite R-ASPP decoder, and a novel reparameterizable classification head - to decouple training-time capacity from inference-time latency. We also introduce a comprehensive waterhemp dataset containing 10,264 annotated frames from 23 plants. On this benchmark, WeedRepFormer achieves 92.18% mIoU for segmentation and 81.91% accuracy for gender classification using only 3.59M parameters and 3.80 GFLOPs. At 108.95 FPS, our model outperforms the state-of-the-art iFormer-T by 4.40% in classification accuracy while maintaining competitive segmentation performance and significantly reducing parameter count by 1.9x. △ Less

Submitted 6 January, 2026; originally announced January 2026.

Comments: 11 pages, 5 figures

Entropy-Aligned Decoding of LMs for Better Writing and Reasoning

Authors: Kareem Ahmed, Sameer Singh

Abstract: Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM distribution to a set of high-probability continuations, but rely on greedy heuristics that introduce myopic distortions, yielding sentences that are homogeneous, repet… ▽ More Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM distribution to a set of high-probability continuations, but rely on greedy heuristics that introduce myopic distortions, yielding sentences that are homogeneous, repetitive and incoherent. In this paper, we introduce EPIC, a hyperparameter-free decoding approach that incorporates the entropy of future trajectories into LM decoding. EPIC explicitly regulates the amount of uncertainty expressed at every step of generation, aligning the sampling distribution's entropy to the aleatoric (data) uncertainty. Through Entropy-Aware Lazy Gumbel-Max sampling, EPIC manages to be exact, while also being efficient, requiring only a sublinear number of entropy evaluations per step. Unlike current baselines, EPIC yields sampling distributions that are empirically well-aligned with the entropy of the underlying data distribution. Across creative writing and summarization tasks, EPIC consistently improves LM-as-judge preference win-rates over widely used decoding strategies. These preference gains are complemented by automatic metrics, showing that EPIC produces more diverse generations and more faithful summaries. We also evaluate EPIC on mathematical reasoning, where it outperforms all baselines. △ Less

Submitted 4 January, 2026; originally announced January 2026.

SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code

Authors: Shima Imani, Seungwhan Moon, Adel Ahmadyan, Lu Zhang, Kirmani Ahmed, Babak Damavandi

Abstract: We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied by structured, step-by-step reasoning and executable Python code that produces the ground-truth solution for any parameter set. The benchmark contains three qu… ▽ More We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied by structured, step-by-step reasoning and executable Python code that produces the ground-truth solution for any parameter set. The benchmark contains three question types: MC-Symbolic (multiple-choice with symbolic options), MC-Numerical (multiple-choice with numerical options), and free-form (open-ended responses). These diverse formats test complementary reasoning skills. By leveraging the dynamic, code-driven nature of the benchmark, we introduce three novel evaluation metrics in addition to standard accuracy: Consistency Score, Failure Rate, and Confusion Rate, that quantify variability and uncertainty across problem variants. Experiments with state-of-the-art instruction-tuned language models reveal both strengths and limitations in scientific reasoning, positioning SymPyBench as a foundation for developing more robust and interpretable reasoning systems △ Less

Submitted 5 December, 2025; originally announced December 2025.

PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation

Authors: Shima Imani, Seungwhan Moon, Adel Ahmadyan, Lu Zhang, Kirmani Ahmed, Babak Damavandi

Abstract: Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic reasoning, and adherence to formal laws, requirements that most existing benchmarks fail to address. In particular, current datasets tend to be static, lacking intermediate reasoning… ▽ More Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic reasoning, and adherence to formal laws, requirements that most existing benchmarks fail to address. In particular, current datasets tend to be static, lacking intermediate reasoning steps, robustness to variations, or mechanisms for verifying scientific correctness. To address these limitations, we introduce PRiSM, a synthetic, fully dynamic, and multimodal benchmark for evaluating scientific reasoning via grounded Python code. PRiSM includes over 24,750 university-level physics and math problems, and it leverages our scalable agent-based pipeline, PrismAgent, to generate well-structured problem instances. Each problem contains dynamic textual and visual input, a generated figure, alongside rich structured outputs: executable Python code for ground truth generation and verification, and detailed step-by-step reasoning. The dynamic nature and Python-powered automated ground truth generation of our benchmark allow for fine-grained experimental auditing of multimodal VLMs, revealing failure modes, uncertainty behaviors, and limitations in scientific reasoning. To this end, we propose five targeted evaluation tasks covering generalization, symbolic program synthesis, perturbation robustness, reasoning correction, and ambiguity resolution. Through comprehensive evaluation of existing VLMs, we highlight their limitations and showcase how PRiSM enables deeper insights into their scientific reasoning capabilities. △ Less

Submitted 5 December, 2025; originally announced December 2025.

WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios

Authors: Eun Chang, Zhuangqun Huang, Yiwei Liao, Sagar Ravi Bhavsar, Amogh Param, Tammy Stark, Adel Ahmadyan, Xiao Yang, Jiaqi Wang, Ahsan Abdullah, Giang Nguyen, Akil Iyer, David Hall, Elissa Li, Shane Moon, Nicolas Scheffer, Kirmani Ahmed, Babak Damavandi, Rakesh Wanga, Anuj Kumar, Rohit Patel, Xin Luna Dong

Abstract: We introduce WearVQA, the first benchmark specifically designed to evaluate the Visual Question Answering (VQA) capabilities of multi-model AI assistant on wearable devices like smart glasses. Unlike prior benchmarks that focus on high-quality, third-person imagery, WearVQA reflects the unique challenges of ego-centric interaction-where visual inputs may be occluded, poorly lit, unzoomed, or blurr… ▽ More We introduce WearVQA, the first benchmark specifically designed to evaluate the Visual Question Answering (VQA) capabilities of multi-model AI assistant on wearable devices like smart glasses. Unlike prior benchmarks that focus on high-quality, third-person imagery, WearVQA reflects the unique challenges of ego-centric interaction-where visual inputs may be occluded, poorly lit, unzoomed, or blurry, and questions are grounded in realistic wearable use cases. The benchmark comprises 2,520 carefully curated image-question-answer triplets, spanning 7 diverse image domains including both text-centric and general scenes, 10 cognitive task types ranging from basic recognition to various forms of reasoning, and 6 common wearables-specific image quality issues. All questions are designed to be answerable using only the visual input and common senses. WearVQA is paired with a rigorous LLM-as-a-judge evaluation framework with 96% labeling accuracy. Open-source and proprietary multi-model LLMs achieved a QA accuracy as low as 24-52% on WearVQA, with substantial drops on lower-quality images and reasoning-heavy tasks. These observations position WearVQA as a comprehensive and challenging benchmark for guiding technical advancement towards robust, real-world multi-model wearables AI systems. △ Less

Submitted 2 December, 2025; v1 submitted 27 November, 2025; originally announced November 2025.

Comments: 11 pages, 5 figures, NeurIPS 2025

Iterative Critique-Refine Framework for Enhancing LLM Personalization

Authors: Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao, Gayathri Akkinapalli, Franck Dernoncourt, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed

Abstract: Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented approaches such as LaMP and PGraphRAG enrich profiles with user and neighbor histories, but they stop at generation and often yield outputs that drift in tone, topic, or style. We present PerFine, a unified, training-free… ▽ More Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented approaches such as LaMP and PGraphRAG enrich profiles with user and neighbor histories, but they stop at generation and often yield outputs that drift in tone, topic, or style. We present PerFine, a unified, training-free critique-refine framework that enhances personalization through iterative, profile-grounded feedback. In each iteration, an LLM generator produces a draft conditioned on the retrieved profile, and a critic LLM - also conditioned on the same profile - provides structured feedback on tone, vocabulary, sentence structure, and topicality. The generator then revises, while a novel knockout strategy retains the stronger draft across iterations. We further study additional inference-time strategies such as Best-of-N and Topic Extraction to balance quality and efficiency. Across Yelp, Goodreads, and Amazon datasets, PerFine consistently improves personalization over PGraphRAG, with GEval gains of +7-13%, steady improvements over 3-5 refinement iterations, and scalability with increasing critic size. These results highlight that post-hoc, profile-aware feedback offers a powerful paradigm for personalized LLM generation that is both training-free and model-agnostic. △ Less

Submitted 28 October, 2025; originally announced October 2025.

ArmFormer: Lightweight Transformer Architecture for Real-Time Multi-Class Weapon Segmentation and Classification

Authors: Akhila Kambhatla, Taminul Islam, Khaled R Ahmed

Abstract: The escalating threat of weapon-related violence necessitates automated detection systems capable of pixel-level precision for accurate threat assessment in real-time security applications. Traditional weapon detection approaches rely on object detection frameworks that provide only coarse bounding box localizations, lacking the fine-grained segmentation required for comprehensive threat analysis.… ▽ More The escalating threat of weapon-related violence necessitates automated detection systems capable of pixel-level precision for accurate threat assessment in real-time security applications. Traditional weapon detection approaches rely on object detection frameworks that provide only coarse bounding box localizations, lacking the fine-grained segmentation required for comprehensive threat analysis. Furthermore, existing semantic segmentation models either sacrifice accuracy for computational efficiency or require excessive computational resources incompatible with edge deployment scenarios. This paper presents ArmFormer, a lightweight transformer-based semantic segmentation framework that strategically integrates Convolutional Block Attention Module (CBAM) with MixVisionTransformer architecture to achieve superior accuracy while maintaining computational efficiency suitable for resource-constrained edge devices. Our approach combines CBAM-enhanced encoder backbone with attention-integrated hamburger decoder to enable multi-class weapon segmentation across five categories: handgun, rifle, knife, revolver, and human. Comprehensive experiments demonstrate that ArmFormer achieves state-of-the-art performance with 80.64% mIoU and 89.13% mFscore while maintaining real-time inference at 82.26 FPS. With only 4.886G FLOPs and 3.66M parameters, ArmFormer outperforms heavyweight models requiring up to 48x more computation, establishing it as the optimal solution for deployment on portable security cameras, surveillance drones, and embedded AI accelerators in distributed security infrastructure. △ Less

Submitted 19 October, 2025; originally announced October 2025.

Comments: 9 pages with 4 figures and 5 tables. This is a preprint submitted to arXiv

MSC Class: 68T07 ACM Class: I.2.10; I.5.4; I.4.6

WaveNet's Precision in EEG Classification

Authors: Casper van Laar, Khubaib Ahmed

Abstract: This study introduces a WaveNet-based deep learning model designed to automate the classification of intracranial electroencephalography (iEEG) signals into physiological activity, pathological (epileptic) activity, power-line noise, and other non-cerebral artifacts. Traditional methods for iEEG signal classification, which rely on expert visual review, are becoming increasingly impractical due to… ▽ More This study introduces a WaveNet-based deep learning model designed to automate the classification of intracranial electroencephalography (iEEG) signals into physiological activity, pathological (epileptic) activity, power-line noise, and other non-cerebral artifacts. Traditional methods for iEEG signal classification, which rely on expert visual review, are becoming increasingly impractical due to the growing complexity and volume of iEEG recordings. Leveraging a publicly available annotated dataset from Mayo Clinic and St. Anne's University Hospital, the WaveNet model was trained, validated, and tested on 209,231 samples using a 70/20/10 split. The model achieved a classification accuracy exceeding previous non-specialized CNN- and LSTM-based approaches and was benchmarked against a Temporal Convolutional Network (TCN) baseline. Notably, the model achieves high discrimination of noise and artifact classes, with precisions of 0.98 and approximately 1, respectively. Classification between physiological and pathological signals exhibits a modest but clinically interpretable overlap, with F1-scores of 0.96 and 0.90 and 175 and 272 cross-class false positives, respectively, reflecting inherent clinical overlap. WaveNet's architecture, originally developed for raw audio synthesis, is well-suited for iEEG data due to its use of dilated causal convolutions and residual connections, enabling the capture of both fine-grained and long-range temporal dependencies. The study also details the preprocessing pipeline, including dynamic dataset partitioning, the use of focal loss to address class imbalance, and normalization steps that support high model performance. While the results demonstrate strong in-distribution performance, generalizability across datasets and clinical settings has yet to be established. △ Less

Submitted 12 January, 2026; v1 submitted 10 October, 2025; originally announced October 2025.

Comments: 6 pages, 5 figures and 3 tables. Includes main text and bibliography

MSC Class: 68T07; 92C55; 62M10 ACM Class: I.2.6; I.5.1; J.3

Turbulence Closure in RANS and Flow Inference around a Cylinder using PINNs and Sparse Experimental Data

Authors: Z. Zhang, K. Shukla, Z. Wang, A. Morales, T. Käufer, S. Salauddin, N. Walters, D. Barrett, K. Ahmed, M. S. Triantafyllou, G. E. Karniadakis

Abstract: Traditional Reynolds-averaged Navier-Stokes (RANS) closures, based on the Boussinesq eddy viscosity hypothesis and calibrated on canonical flows, often yield inaccurate predictions of both mean flow and turbulence statistics. Here, we consider flow past a circular cylinder over a range of Reynolds numbers (3,900-100,000) and Mach numbers (0-0.3), encompassing incompressible and weakly compressible… ▽ More Traditional Reynolds-averaged Navier-Stokes (RANS) closures, based on the Boussinesq eddy viscosity hypothesis and calibrated on canonical flows, often yield inaccurate predictions of both mean flow and turbulence statistics. Here, we consider flow past a circular cylinder over a range of Reynolds numbers (3,900-100,000) and Mach numbers (0-0.3), encompassing incompressible and weakly compressible regimes, with the goal of improving predictions of mean velocity and Reynolds stresses. To this end, we assemble a cross-validated dataset comprising hydrodynamic particle image velocimetry (PIV) in a towing tank, aerodynamic PIV in a wind tunnel, and high-fidelity spectral element DNS and LES. Analysis of these data reveals a universal distribution of Reynolds stresses across the parameter space, which provides the foundation for a data-driven closure. We employ physics-informed neural networks (PINNs), trained with the unclosed RANS equations, to infer the velocity field and Reynolds-stress forcing from boundary information alone. The resulting closure, embedded in a forward PINN solver, significantly improves RANS predictions of both mean flow and turbulence statistics relative to conventional models. △ Less

Submitted 7 October, 2025; originally announced October 2025.

Comments: 36 pages, 39 figures

Destroying the Kerr Newman MOG Black hole with Scalar Test Field

Authors: Waqar Ahmad, Abdul Rehman Kashif, Ayyesha K. Ahmed

Abstract: We test the weak cosmic censorship conjecture (WCCC) for the Kerr-Newman-modified gravity black hole (KN-MOG-BH) by interacting scalar test fields with the KN-MOG-BH. Neglecting backreaction effects, we first show that the scalar test fields with frequencies just above the superradiance threshold can overspin both extremal and nearly extremal KN-MOG-BHs, leading to the formation of naked singulari… ▽ More We test the weak cosmic censorship conjecture (WCCC) for the Kerr-Newman-modified gravity black hole (KN-MOG-BH) by interacting scalar test fields with the KN-MOG-BH. Neglecting backreaction effects, we first show that the scalar test fields with frequencies just above the superradiance threshold can overspin both extremal and nearly extremal KN-MOG-BHs, leading to the formation of naked singularities. Moreover, test fields can continuously push nearly extremal KN-MOG-BHs toward their extremal limit. Next, we incorporate backreaction effects, assuming that the event horizon's angular velocity rises prior to the test field's absorption. We show that backreaction prevents overspinning in the extremal KN-MOG-BH, whereas in the nearly extremal case, it fails to stop the BH from being overspun. △ Less

Submitted 22 September, 2025; originally announced September 2025.

Spherical Accretion on a Schwarzschild-MOG Black Hole

Authors: Ayyesha K. Ahmed, M Z A Moughal

Abstract: In this paper we have examined spherical accretion onto Schwarzschild MOG Black Holes within the framework of Modified Gravity. Using isothermal test fluids, we analyze the behavior of the flow near the critical (sonic) point for various values of the equation of state parameter $k$. Depending on the fluid type, the flow exhibits either subsonic or supersonic behavior, with ultra-stiff and ultra-r… ▽ More In this paper we have examined spherical accretion onto Schwarzschild MOG Black Holes within the framework of Modified Gravity. Using isothermal test fluids, we analyze the behavior of the flow near the critical (sonic) point for various values of the equation of state parameter $k$. Depending on the fluid type, the flow exhibits either subsonic or supersonic behavior, with ultra-stiff and ultra-relativistic fluids allowing both regimes, while radiation and sub-relativistic fluids show more restricted dynamics. Phase space analysis helps visualize these transitions. We also compute the mass accretion rate and find that it increases with both radial distance and the MOG parameter $α$, highlighting the role of modified gravity in enhancing accretion processes around black holes △ Less

Submitted 30 October, 2025; v1 submitted 6 September, 2025; originally announced September 2025.

DSROQ: Dynamic Scheduling and Routing for QoE Management in LEO Satellite Networks

Authors: Dhiraj Bhattacharjee, Pablo G. Madoery, Abhishek Naik, Halim Yanikomeroglu, Gunes Karabulut Kurt, Stephane Martel, Khaled Ahmed

Abstract: The modern Internet supports diverse applications with heterogeneous quality of service (QoS) requirements. Low Earth orbit (LEO) satellite constellations offer a promising solution to meet these needs, enhancing coverage in rural areas and complementing terrestrial networks in urban regions. Ensuring QoS in such networks requires joint optimization of routing, bandwidth allocation, and dynamic qu… ▽ More The modern Internet supports diverse applications with heterogeneous quality of service (QoS) requirements. Low Earth orbit (LEO) satellite constellations offer a promising solution to meet these needs, enhancing coverage in rural areas and complementing terrestrial networks in urban regions. Ensuring QoS in such networks requires joint optimization of routing, bandwidth allocation, and dynamic queue scheduling, as traffic handling is critical for maintaining service performance. This paper formulates a joint routing and bandwidth allocation problem where QoS requirements are treated as soft constraints, aiming to maximize user experience. An adaptive scheduling approach is introduced to prioritize flow-specific QoS needs. We propose a Monte Carlo tree search (MCTS)-inspired method to solve the NP-hard route and bandwidth allocation problem, with Lyapunov optimization-based scheduling applied during reward evaluation. Using the Starlink Phase 1 Version 2 constellation, we compare end-user experience and fairness between our proposed DSROQ algorithm and a benchmark scheme. Results show that DSROQ improves both performance metrics and demonstrates the advantage of joint routing and bandwidth decisions. Furthermore, we observe that the dominant performance factor shifts from scheduling to routing and bandwidth allocation as traffic sensitivity changes from latency-driven to bandwidth-driven. △ Less

Submitted 28 August, 2025; originally announced August 2025.

Structural Damage Detection Using AI Super Resolution and Visual Language Model

Authors: Catherine Hoier, Khandaker Mamun Ahmed

Abstract: Natural disasters pose significant challenges to timely and accurate damage assessment due to their sudden onset and the extensive areas they affect. Traditional assessment methods are often labor-intensive, costly, and hazardous to personnel, making them impractical for rapid response, especially in resource-limited settings. This study proposes a novel, cost-effective framework that leverages ae… ▽ More Natural disasters pose significant challenges to timely and accurate damage assessment due to their sudden onset and the extensive areas they affect. Traditional assessment methods are often labor-intensive, costly, and hazardous to personnel, making them impractical for rapid response, especially in resource-limited settings. This study proposes a novel, cost-effective framework that leverages aerial drone footage, an advanced AI-based video super-resolution model, Video Restoration Transformer (VRT), and Gemma3:27b, a 27 billion parameter Visual Language Model (VLM). This integrated system is designed to improve low-resolution disaster footage, identify structural damage, and classify buildings into four damage categories, ranging from no/slight damage to total destruction, along with associated risk levels. The methodology was validated using pre- and post-event drone imagery from the 2023 Turkey earthquakes (courtesy of The Guardian) and satellite data from the 2013 Moore Tornado (xBD dataset). The framework achieved a classification accuracy of 84.5%, demonstrating its ability to provide highly accurate results. Furthermore, the system's accessibility allows non-technical users to perform preliminary analyses, thereby improving the responsiveness and efficiency of disaster management efforts. △ Less

Submitted 23 August, 2025; originally announced August 2025.

Journal ref: International Conference on Machine Learning and Applications, 2025

GasTwinFormer: A Hybrid Vision Transformer for Livestock Methane Emission Segmentation and Dietary Classification in Optical Gas Imaging

Authors: Toqi Tahamid Sarker, Mohamed Embaby, Taminul Islam, Amer AbuGhazaleh, Khaled R Ahmed

Abstract: Livestock methane emissions represent 32% of human-caused methane production, making automated monitoring critical for climate mitigation strategies. We introduce GasTwinFormer, a hybrid vision transformer for real-time methane emission segmentation and dietary classification in optical gas imaging through a novel Mix Twin encoder alternating between spatially-reduced global attention and locally-… ▽ More Livestock methane emissions represent 32% of human-caused methane production, making automated monitoring critical for climate mitigation strategies. We introduce GasTwinFormer, a hybrid vision transformer for real-time methane emission segmentation and dietary classification in optical gas imaging through a novel Mix Twin encoder alternating between spatially-reduced global attention and locally-grouped attention mechanisms. Our architecture incorporates a lightweight LR-ASPP decoder for multi-scale feature aggregation and enables simultaneous methane segmentation and dietary classification in a unified framework. We contribute the first comprehensive beef cattle methane emission dataset using OGI, containing 11,694 annotated frames across three dietary treatments. GasTwinFormer achieves 74.47% mIoU and 83.63% mF1 for segmentation while maintaining exceptional efficiency with only 3.348M parameters, 3.428G FLOPs, and 114.9 FPS inference speed. Additionally, our method achieves perfect dietary classification accuracy (100%), demonstrating the effectiveness of leveraging diet-emission correlations. Extensive ablation studies validate each architectural component, establishing GasTwinFormer as a practical solution for real-time livestock emission monitoring. Please see our project page at gastwinformer.github.io. △ Less

Submitted 20 August, 2025; originally announced August 2025.

Comments: Accepted for publication at ICCVW 2025

WeedSense: Multi-Task Learning for Weed Segmentation, Height Estimation, and Growth Stage Classification

Authors: Toqi Tahamid Sarker, Khaled R Ahmed, Taminul Islam, Cristiana Bernardi Rankrape, Karla Gage

Abstract: Weed management represents a critical challenge in agriculture, significantly impacting crop yields and requiring substantial resources for control. Effective weed monitoring and analysis strategies are crucial for implementing sustainable agricultural practices and site-specific management approaches. We introduce WeedSense, a novel multi-task learning architecture for comprehensive weed analysis… ▽ More Weed management represents a critical challenge in agriculture, significantly impacting crop yields and requiring substantial resources for control. Effective weed monitoring and analysis strategies are crucial for implementing sustainable agricultural practices and site-specific management approaches. We introduce WeedSense, a novel multi-task learning architecture for comprehensive weed analysis that jointly performs semantic segmentation, height estimation, and growth stage classification. We present a unique dataset capturing 16 weed species over an 11-week growth cycle with pixel-level annotations, height measurements, and temporal labels. WeedSense leverages a dual-path encoder incorporating Universal Inverted Bottleneck blocks and a Multi-Task Bifurcated Decoder with transformer-based feature fusion to generate multi-scale features and enable simultaneous prediction across multiple tasks. WeedSense outperforms other state-of-the-art models on our comprehensive evaluation. On our multi-task dataset, WeedSense achieves mIoU of 89.78% for segmentation, 1.67cm MAE for height estimation, and 99.99% accuracy for growth stage classification while maintaining real-time inference at 160 FPS. Our multitask approach achieves 3$\times$ faster inference than sequential single-task execution and uses 32.4% fewer parameters. Please see our project page at weedsense.github.io. △ Less

Submitted 20 August, 2025; originally announced August 2025.

Comments: This paper has been submitted and accepted for publication at ICCVW 2025

Sub- μ W Battery-Less and Oscillator-Less Wi-Fi Backscattering Transmitter Reusing RF Signal for Harvesting, Communications, and Motion Detection

Authors: Marco Privitera, Andrea Ballo, Karim Ali Ahmed, Alfio Dario Grasso, Massimo Alioto

Abstract: In this paper, a sub-uW power 802.11b backscattering transmitter is presented to enable reuse of the same incident wave for three purposes: RF harvesting, backscattering communications and position/motion sensing. The removal of the battery and any off-chip motion sensor (e.g., MEMS) enables unprecedented level of miniaturization and ubiquity, unrestricted device lifespan, low fabrication and main… ▽ More In this paper, a sub-uW power 802.11b backscattering transmitter is presented to enable reuse of the same incident wave for three purposes: RF harvesting, backscattering communications and position/motion sensing. The removal of the battery and any off-chip motion sensor (e.g., MEMS) enables unprecedented level of miniaturization and ubiquity, unrestricted device lifespan, low fabrication and maintenance cost. The uW power wall for WiFi transmitters is broken for the first time via local oscillator elimination, as achieved by extracting its frequency through second-order intermodulation of a twotone incident wave. The two-tone scheme also enables a cumulative harvesting/transmission/sensing sensitivity down to Pmin -19 dBm. Position/motion sensing is enabled by using the harvested voltage as a proxy for the Received Signal Strength (RSS), allowing to sense the chip location with respect to the tone generator(s) shared across tags in indoor neighborhoods. △ Less

Submitted 7 August, 2025; originally announced August 2025.

DIRF: A Framework for Digital Identity Protection and Clone Governance in Agentic AI Systems

Authors: Hammad Atta, Muhammad Zeeshan Baig, Yasir Mehmood, Nadeem Shahzad, Ken Huang, Muhammad Aziz Ul Haq, Muhammad Awais, Kamal Ahmed, Anthony Green

Abstract: The rapid advancement and widespread adoption of generative artificial intelligence (AI) pose significant threats to the integrity of personal identity, including digital cloning, sophisticated impersonation, and the unauthorized monetization of identity-related data. Mitigating these risks necessitates the development of robust AI-generated content detection systems, enhanced legal frameworks, an… ▽ More The rapid advancement and widespread adoption of generative artificial intelligence (AI) pose significant threats to the integrity of personal identity, including digital cloning, sophisticated impersonation, and the unauthorized monetization of identity-related data. Mitigating these risks necessitates the development of robust AI-generated content detection systems, enhanced legal frameworks, and ethical guidelines. This paper introduces the Digital Identity Rights Framework (DIRF), a structured security and governance model designed to protect behavioral, biometric, and personality-based digital likeness attributes to address this critical need. Structured across nine domains and 63 controls, DIRF integrates legal, technical, and hybrid enforcement mechanisms to secure digital identity consent, traceability, and monetization. We present the architectural foundations, enforcement strategies, and key use cases supporting the need for a unified framework. This work aims to inform platform builders, legal entities, and regulators about the essential controls needed to enforce identity rights in AI-driven systems. △ Less

Submitted 8 September, 2025; v1 submitted 3 August, 2025; originally announced August 2025.

Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation

Authors: Leyao Wang, Xutao Mao, Xuhui Zhan, Yuying Zhao, Bo Ni, Ryan A. Rossi, Nesreen K. Ahmed, Tyler Derr

Abstract: Textual reviews enrich recommender systems with fine-grained preference signals and enhanced explainability. However, in real-world scenarios, users rarely leave reviews, resulting in severe sparsity that undermines the effectiveness of existing models. A natural solution is to impute or generate missing reviews to enrich the data. However, conventional imputation techniques -- such as matrix comp… ▽ More Textual reviews enrich recommender systems with fine-grained preference signals and enhanced explainability. However, in real-world scenarios, users rarely leave reviews, resulting in severe sparsity that undermines the effectiveness of existing models. A natural solution is to impute or generate missing reviews to enrich the data. However, conventional imputation techniques -- such as matrix completion and LLM-based augmentation -- either lose contextualized semantics by embedding texts into vectors, or overlook structural dependencies among user-item interactions. To address these shortcomings, we propose TWISTER (ToWards Imputation on Sparsity with Textual Edge Graph Representation), a unified framework that imputes missing reviews by jointly modeling semantic and structural signals. Specifically, we represent user-item interactions as a Textual-Edge Graph (TEG), treating reviews as edge attributes. To capture relational context, we construct line-graph views and employ a large language model as a graph-aware aggregator. For each interaction lacking a textual review, our model aggregates the neighborhood's natural-language representations to generate a coherent and personalized review. Experiments on the Amazon and Goodreads datasets show that TWISTER consistently outperforms traditional numeric, graph-based, and LLM baselines, delivering higher-quality imputed reviews and, more importantly, enhanced recommendation performance. In summary, TWISTER generates reviews that are more helpful, authentic, and specific, while smoothing structural signals for improved recommendations. △ Less

Submitted 1 August, 2025; originally announced August 2025.

Comments: 13 pages

MCeT: Behavioral Model Correctness Evaluation using Large Language Models

Authors: Khaled Ahmed, Jialing Song, Boqi Chen, Ou Wei, Bingzhou Zheng

Abstract: Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing use of Large Language Models (LLM) as AI modeling assistants, more automation will be involved in generating diagrams. This necessitates the advancement of auto… ▽ More Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing use of Large Language Models (LLM) as AI modeling assistants, more automation will be involved in generating diagrams. This necessitates the advancement of automatic model correctness evaluation tools. Such a tool can be used to evaluate both manually and AI automatically generated models; to provide feedback to system engineers, and enable AI assistants to self-evaluate and self-enhance their generated models. In this paper, we propose MCeT, the first fully automated tool to evaluate the correctness of a behavioral model, sequence diagrams in particular, against its corresponding requirements text and produce a list of issues that the model has. We utilize LLMs for the correctness evaluation tasks as they have shown outstanding natural language understanding ability. However, we show that directly asking an LLM to compare a diagram to requirements finds less than 35% of issues that experienced engineers can find. We propose to supplement the direct check with a fine-grained, multi-perspective approach; we split the diagram into atomic, non-divisible interactions, and split the requirements text into atomic, self-contained items. We compare the diagram with atomic requirements and each diagram-atom with the requirements. We also propose a self-consistency checking approach that combines perspectives to mitigate LLM hallucinated issues. Our combined approach improves upon the precision of the direct approach from 0.58 to 0.81 in a dataset of real requirements. Moreover, the approach finds 90% more issues that the experienced engineers found than the direct approach, and reports an average of 6 new issues per diagram. △ Less

Submitted 30 August, 2025; v1 submitted 1 August, 2025; originally announced August 2025.

Comments: MODELS 2025

Dynamic Activation and Assignment of SDN Controllers in LEO Satellite Constellations

Authors: Wafa Hasanain, Pablo G. Madoery, Halim Yanikomeroglu, Gunes Karabulut Kurt, Sameera Siddiqui, Stephane Martel, Khaled Ahmed, Colin Bellinger

Abstract: Software-defined networking (SDN) has emerged as a promising approach for managing traditional satellite communication. This enhances opportunities for future services, including integrating satellite and terrestrial networks. In this paper, we have developed an SDN-enabled framework for Low Earth Orbit (LEO) satellite networks, incorporating the OpenFlow protocol, all within an OMNeT++ simulation… ▽ More Software-defined networking (SDN) has emerged as a promising approach for managing traditional satellite communication. This enhances opportunities for future services, including integrating satellite and terrestrial networks. In this paper, we have developed an SDN-enabled framework for Low Earth Orbit (LEO) satellite networks, incorporating the OpenFlow protocol, all within an OMNeT++ simulation environment. Dynamic controller assignment is one of the most significant challenges for large LEO constellations. Due to the movement of LEO satellites, satellite-controller assignments must be updated frequently to maintain low propagation delays. To address this issue, we present a dynamic satellite-to-controller assignment (DSCA) optimization problem that continuously adjusts these assignments. Our optimal DSCA (Opt-DSCA) approach minimizes propagation delay and optimizes the number of active controllers. Our preliminary results demonstrate that the DSCA approach significantly outperforms the static satellite-to-controller assignment (SSCA) approach. While SSCA may perform better with more controllers, this scheme fails to adapt to satellite movements. Our DSCA approach consistently improves network efficiency by dynamically reassigning satellites based on propagation delays. Further, we found diminishing returns when the number of controllers is increased beyond a certain point, suggesting optimal performance with a limited number of controllers. Opt-DSCA lowers propagation delays and improves network performance by optimizing satellite assignments and reducing active controllers. △ Less

Submitted 22 July, 2025; originally announced July 2025.

QSAF: A Novel Mitigation Framework for Cognitive Degradation in Agentic AI

Authors: Hammad Atta, Muhammad Zeeshan Baig, Yasir Mehmood, Nadeem Shahzad, Ken Huang, Muhammad Aziz Ul Haq, Muhammad Awais, Kamal Ahmed

Abstract: We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems. Unlike traditional adversarial external threats such as prompt injection, these failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression. These systemic weaknesses lead to silent agent drift, logic collapse, and persistent hallucinations over ti… ▽ More We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems. Unlike traditional adversarial external threats such as prompt injection, these failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression. These systemic weaknesses lead to silent agent drift, logic collapse, and persistent hallucinations over time. To address this class of failures, we introduce the Qorvex Security AI Framework for Behavioral & Cognitive Resilience (QSAF Domain 10), a lifecycle-aware defense framework defined by a six-stage cognitive degradation lifecycle. The framework includes seven runtime controls (QSAF-BC-001 to BC-007) that monitor agent subsystems in real time and trigger proactive mitigation through fallback routing, starvation detection, and memory integrity enforcement. Drawing from cognitive neuroscience, we map agentic architectures to human analogs, enabling early detection of fatigue, starvation, and role collapse. By introducing a formal lifecycle and real-time mitigation controls, this work establishes Cognitive Degradation as a critical new class of AI system vulnerability and proposes the first cross-platform defense model for resilient agentic behavior. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Toxicity in State Sponsored Information Operations

Authors: Ashfaq Ali Shafin, Khandaker Mamun Ahmed

Abstract: State-sponsored information operations (IOs) increasingly influence global discourse on social media platforms, yet their emotional and rhetorical strategies remain inadequately characterized in scientific literature. This study presents the first comprehensive analysis of toxic language deployment within such campaigns, examining 56 million posts from over 42 thousand accounts linked to 18 distin… ▽ More State-sponsored information operations (IOs) increasingly influence global discourse on social media platforms, yet their emotional and rhetorical strategies remain inadequately characterized in scientific literature. This study presents the first comprehensive analysis of toxic language deployment within such campaigns, examining 56 million posts from over 42 thousand accounts linked to 18 distinct geopolitical entities on X/Twitter. Using Google's Perspective API, we systematically detect and quantify six categories of toxic content and analyze their distribution across national origins, linguistic structures, and engagement metrics, providing essential information regarding the underlying patterns of such operations. Our findings reveal that while toxic content constitutes only 1.53% of all posts, they are associated with disproportionately high engagement and appear to be strategically deployed in specific geopolitical contexts. Notably, toxic content originating from Russian influence operations receives significantly higher user engagement compared to influence operations from any other country in our dataset. Our code is available at https://github.com/shafin191/Toxic_IO. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Comments: Accepted at 36th ACM Conference on Hypertext and Social Media (HT '25), September 15-18, 2025, Chicago, IL. 4 pages, 3 figures, 1 table

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems

Authors: Hammad Atta, Ken Huang, Manish Bhatt, Kamal Ahmed, Muhammad Aziz Ul Haq, Yasir Mehmood

Abstract: The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces Logic-layer Prompt Control Injection (LPCI), a novel category of attacks that embeds encoded, delayed, and conditionally triggered payloads within memory, vector stores… ▽ More The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces Logic-layer Prompt Control Injection (LPCI), a novel category of attacks that embeds encoded, delayed, and conditionally triggered payloads within memory, vector stores, or tool outputs. These payloads can bypass conventional input filters and trigger unauthorised behaviour across sessions. △ Less

Submitted 6 August, 2025; v1 submitted 14 July, 2025; originally announced July 2025.

TritonZ: A Remotely Operated Underwater Rover with Manipulator Arm for Exploration and Rescue Operations

Authors: Kawser Ahmed, Mir Shahriar Fardin, Md Arif Faysal Nayem, Fahim Hafiz, Swakkhar Shatabda

Abstract: The increasing demand for underwater exploration and rescue operations enforces the development of advanced wireless or semi-wireless underwater vessels equipped with manipulator arms. This paper presents the implementation of a semi-wireless underwater vehicle, "TritonZ" equipped with a manipulator arm, tailored for effective underwater exploration and rescue operations. The vehicle's compact des… ▽ More The increasing demand for underwater exploration and rescue operations enforces the development of advanced wireless or semi-wireless underwater vessels equipped with manipulator arms. This paper presents the implementation of a semi-wireless underwater vehicle, "TritonZ" equipped with a manipulator arm, tailored for effective underwater exploration and rescue operations. The vehicle's compact design enables deployment in different submarine surroundings, addressing the need for wireless systems capable of navigating challenging underwater terrains. The manipulator arm can interact with the environment, allowing the robot to perform sophisticated tasks during exploration and rescue missions in emergency situations. TritonZ is equipped with various sensors such as Pi-Camera, Humidity, and Temperature sensors to send real-time environmental data. Our underwater vehicle controlled using a customized remote controller can navigate efficiently in the water where Pi-Camera enables live streaming of the surroundings. Motion control and video capture are performed simultaneously using this camera. The manipulator arm is designed to perform various tasks, similar to grasping, manipulating, and collecting underwater objects. Experimental results shows the efficacy of the proposed remotely operated vehicle in performing a variety of underwater exploration and rescue tasks. Additionally, the results show that TritonZ can maintain an average of 13.5cm/s with a minimal delay of 2-3 seconds. Furthermore, the vehicle can sustain waves underwater by maintaining its position as well as average velocity. The full project details and source code can be accessed at this link: https://github.com/kawser-ahmed-byte/TritonZ △ Less

Submitted 27 June, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

Comments: 7 pages, 5 figures

Journal ref: In: 2024 27th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar, Bangladesh, 20-22 December 2024, pp. 417-422

Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition

Authors: Mayank Bumb, Anshul Vemulapalli, Sri Harsha Vardhan Prasad Jella, Anish Gupta, An La, Ryan A. Rossi, Hongjie Chen, Franck Dernoncourt, Nesreen K. Ahmed, Yu Wang

Abstract: Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we explore simple and flexible prompt-based strategies that enable LLMs to perform time series forecasting without extensive retraining or the use of a complex ext… ▽ More Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we explore simple and flexible prompt-based strategies that enable LLMs to perform time series forecasting without extensive retraining or the use of a complex external architecture. Through the exploration of specialized prompting methods that leverage time series decomposition, patch-based tokenization, and similarity-based neighbor augmentation, we find that it is possible to enhance LLM forecasting quality while maintaining simplicity and requiring minimal preprocessing of data. To this end, we propose our own method, PatchInstruct, which enables LLMs to make precise and effective predictions. △ Less

Submitted 15 June, 2025; originally announced June 2025.