Showing 1–50 of 111 results for author: Bilal, M

On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos

Authors: Darakshan Rashid, Raza Imam, Ufaq Khan, Muhammad Bilal, Shazad Ashraf, Dwarikanath Mahapatra, Mohammad Yaqub, Muhammad Haris Khan, Imran Razzak, Brejesh Lall, Lena Maier-Hein, Yutong Xie

Abstract: Temporal vision-language models (TVLMs) offer a reusable, prompt-based interface for surgical video understanding, yet, their robustness under clinically realistic acquisition artifacts in endoscopy remains insufficiently characterized. In practice, degradations such as defocus, haze, motion blur, noise, cautery smoke, and packet loss introduce structured distribution shifts which may compromise v… ▽ More Temporal vision-language models (TVLMs) offer a reusable, prompt-based interface for surgical video understanding, yet, their robustness under clinically realistic acquisition artifacts in endoscopy remains insufficiently characterized. In practice, degradations such as defocus, haze, motion blur, noise, cautery smoke, and packet loss introduce structured distribution shifts which may compromise video-text alignment. We study the robustness of temporal VLMs under such shifts caused by corruptions in clip frames. We introduce Endo-C6, a compact corruption benchmark of six endoscopy-realistic perturbations evaluated at a fixed high severity, and apply it to public Gastrointestinal (GI) endoscopy and laparoscopic cholecystectomy videos. Under a standardized prompt protocol, we benchmark 3 recent surgical TVLM baselines and analyze robustness in both mean and worst-case settings, spanning 294 dataset-level evaluations. Finally, we present RobustEndoCLIP, obtained by few-shot parameter-efficient tuning with VeRA, outperforming existing TVLM baselines. Our findings show that off-the-shelf TVLMs can exhibit severe worst-case collapse under endoscopy-specific corruptions, whereas lightweight few-shot adaptation can substantially improve corrupted performance and robustness without changing the prompt-based interface. We expect Endo-C6 to support standardized robustness reporting and promote more reliable clinical vision-language systems. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: Accepted to MICCAI 2026

From Information to Delegation: Mapping Human-AI Financial Decision Making

Authors: Iman Munire Bilal, Yingcan Carol Wang, Ajan Raj, Filippo Giovagnini, Pranav Tewari, Yuwei Zhang, Mei-Chen Zoe Liou, Qamar Zaman

Abstract: As AI increasingly participates in human decision making, understanding how decision-making authority is distributed between humans and AI has become a fundamental behavioural question. We introduce a behavioural measurement framework combining intent and delegated decision authority to quantify what consumers seek from AI and how much decision-making authority they assign to it. Applied to 1.5 mi… ▽ More As AI increasingly participates in human decision making, understanding how decision-making authority is distributed between humans and AI has become a fundamental behavioural question. We introduce a behavioural measurement framework combining intent and delegated decision authority to quantify what consumers seek from AI and how much decision-making authority they assign to it. Applied to 1.5 million real-world ChatGPT and Gemini interactions from 6,304 users in the United States and India, we find that financial services are already a substantial AI use case. Consumers overwhelmingly use AI to retrieve information and shape financial judgement, while delegation of financial execution remains rare. By shifting attention from conversation topics to delegated decision authority, this work establishes a behavioural baseline for measuring the transition to increasingly agentic AI. △ Less

Submitted 3 August, 2026; originally announced August 2026.

Nova3D: Code-Native Generation of Programmable 3D Assets

Authors: Nimra Noor, Muhammad Bilal, Abdullah Hussain, Hassan Baig

Abstract: Current 3D generative models mostly produce a final surface: a visually strong but largely opaque mesh. Interactive 3D worlds need more than a surface. They need named parts, an assembly hierarchy, measurable constraints, local edit handles, and joints for articulation. We present Nova3D, a system that generates 3D assets as executable Blender source code; the compiled mesh, a binary glTF (GLB), i… ▽ More Current 3D generative models mostly produce a final surface: a visually strong but largely opaque mesh. Interactive 3D worlds need more than a surface. They need named parts, an assembly hierarchy, measurable constraints, local edit handles, and joints for articulation. We present Nova3D, a system that generates 3D assets as executable Blender source code; the compiled mesh, a binary glTF (GLB), is treated as the artifact, not the asset. Because the output is a program, semantic handles exist at generation time rather than being recovered afterward by segmentation or rigging. We evaluate on Nova3D-Bench, a frozen, spec-grounded benchmark of 54 items across six domains and three difficulty levels with text and image inputs, against eleven baselines in four families (mesh-native, part-structured, code-native, and CAD) plus a same-LLM ablation. Nova3D produces an executable program and a valid artifact for 54/54 items. Every asset exposes named parts organized in a parent-child assembly tree; no mesh-native, CAD, or segmentation baseline exposes either. It satisfies 51/52 prompt-stated numeric and count constraints (best baseline: 11/52), passes 14/18 blinded local edits with locality preserved in 18/18, and articulates 59 joints across 12 assets at 98.3% geometric validity, where every baseline exposes zero native joints. Its geometry is competitive: it wins the structured domains in a pairwise shape-quality tournament and is second only to the strongest mesh-native model, while conceding texture realism to baked-PBR systems. The central result is representational: code-native generation turns a generated 3D object from an opaque surface into a programmable asset that downstream systems can inspect, measure, edit, and animate. △ Less

Submitted 22 July, 2026; originally announced July 2026.

LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review

Authors: Ali Hassaan Mughal, Muhammad Bilal

Abstract: Large language models (LLMs) increasingly decide whether software behaves correctly, either by writing a test oracle or by acting as one. Yet two oracles can look identical and rest on different ground: one assertion encodes a written specification, another only what the model learned in training. Prior secondary studies sort oracles by form or by technique, rarely by the property that governs how… ▽ More Large language models (LLMs) increasingly decide whether software behaves correctly, either by writing a test oracle or by acting as one. Yet two oracles can look identical and rest on different ground: one assertion encodes a written specification, another only what the model learned in training. Prior secondary studies sort oracles by form or by technique, rarely by the property that governs how far a verdict can be trusted: where its authority comes from. This systematic literature review, reported under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, screens 2,436 records to 54 included studies, extended by citation searching (snowballing) to 83 in total. We read the corpus along three axes: the source of an oracle's authority, the form it takes, and the mechanism that adjudicates it. Just over half of the corpus reaches a verdict with no specification at all. That is what lets these oracles work on code with no specification to consult, and what leaves a challenged verdict with less to fall back on. Source and mechanism cross-cut rather than coincide, so a label such as LLM-as-a-judge names how a verdict is produced, not why it should be trusted. Oracle quality is most often judged by resemblance to a known oracle rather than by whether injected faults are caught. The first question to ask of any LLM oracle is therefore what one would point to in defending its verdict. The protocol, search query, and per-study coding sheet are released. △ Less

Submitted 13 August, 2026; v1 submitted 6 July, 2026; originally announced July 2026.

Comments: 21 pages, 10 figures, 11 tables. Systematic literature review of 83 studies, reported under PRISMA 2020. Submitted to IEEE Access. Replication package: https://doi.org/10.5281/zenodo.21194940

All Green, Still Broken: Real-Flow Verification Lessons from an LLM-Integrated, Multi-Market Web Application

Authors: Muhammad Bilal, Ali Hassaan Mughal

Abstract: Modern web applications increasingly combine three ingredients that are hard to test: output from large language models, multi-market internationalization, and browser-driven front-ends over external data sources. We report on a production rental-search assistant whose automated suite grew to 1,553 test cases in six weeks. The suite passed continuously, yet user-facing defects continued to reach p… ▽ More Modern web applications increasingly combine three ingredients that are hard to test: output from large language models, multi-market internationalization, and browser-driven front-ends over external data sources. We report on a production rental-search assistant whose automated suite grew to 1,553 test cases in six weeks. The suite passed continuously, yet user-facing defects continued to reach production. We studied all 252 bug-fix commits in the project and classified each by the boundary, or seam, it escaped through. About 44 percent of the fixes fall in four seams that component-level unit tests cannot observe: the live browser runtime, the non-default market, the end-to-end flow, and the whole-system level. A fix without a guard at the seam let one defect ship twice. We present the four-seam framework, the measured defect distribution, and the practices we adopted, including a simple way for a team to find the seam that carries the most fixes. △ Less

Submitted 21 June, 2026; originally announced June 2026.

Comments: 7 pages, 4 figures, 2 tables. Preprint of a manuscript submitted to IEEE Software

ACM Class: D.2.5; D.2.4

AgriGov: A Structured Multilingual Dataset Curation for Indian Government Schemes for Farmers

Authors: Mohsina Bilal, Gopakumar G

Abstract: AgriGov is a curated, trilingual (English-Hindi-Marathi) dataset designed to address the scarcity of domain-grounded multilingual resources for agricultural policies and farmer welfare schemes. Initially, we collected and structured data from 50 government schemes sourced from trusted portals using automated scraping techniques, organizing it into predefined semantic fields (e.g., title, eligibili… ▽ More AgriGov is a curated, trilingual (English-Hindi-Marathi) dataset designed to address the scarcity of domain-grounded multilingual resources for agricultural policies and farmer welfare schemes. Initially, we collected and structured data from 50 government schemes sourced from trusted portals using automated scraping techniques, organizing it into predefined semantic fields (e.g., title, eligibility, application process, documents, exclusions). Translations were performed using a pipeline combining Google Translate API, MarianMT, and human post-editing, resulting in a domain-specific Hindi-Marathi dataset comprising approximately 2100 source segments. To enhance coverage, we augmented this dataset with sentences from the Samanantar corpus, leading to approximately 8,000 sentence-aligned Hindi-Marathi parallel pairs. The dataset now offers robust resources for fine-tuning machine translation models in this domain. AgriGov is designed for applications in domain-adaptive machine translation, question answering, information retrieval, and summarization systems. Its key contribution is a schema-driven, human-corrected multilingual alignment pipeline that ensures domain fidelity, provides provenance, and supports reproducible experiments, enabling retrieval-augmented applications for farmer-facing tools. △ Less

Submitted 6 June, 2026; originally announced June 2026.

Comments: 15 pages, 4 figures, Submitted to: Sadhana, Elsevier

ACM Class: I.2.7; I.2.6; H.3.1

AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigation

Authors: Bilal Hussain, Muhammad Bilal, Tan Li, Haris Pervaiz, Xiao Tang, Qinghe Du, Fawad Ahmad, Muhammad Azhar, Jun Zhang

Abstract: In sixth-generation (6G) networks, billions of cyber-physical systems (CPSs) - autonomous vehicles, smart grids, industrial robots, and remote-surgical equipment - will run over ultra-reliable low-latency slices, collapsing the gap between a remote breach and physical harm to milliseconds, a budget perimeter firewalls and centralised security operations centres cannot meet. This survey reframes 6G… ▽ More In sixth-generation (6G) networks, billions of cyber-physical systems (CPSs) - autonomous vehicles, smart grids, industrial robots, and remote-surgical equipment - will run over ultra-reliable low-latency slices, collapsing the gap between a remote breach and physical harm to milliseconds, a budget perimeter firewalls and centralised security operations centres cannot meet. This survey reframes 6G CPS security as a closed-loop, AI-native pipeline that senses at the multi-access edge computing (MEC) tier, using minute-scale call-detail records (CDRs) for baseline learning and sub-millisecond RAN/Open-RAN (O-RAN) telemetry for the latency-critical path. It decides locally with compressed deep models, mitigates network-wide via SDN, NFV, and O-RAN controllers, and retrains through federated learning (FL) and digital-twin (DT) replay. We formalise a per-slice, tail-bounded latency contract on the sense, detect, and mitigate stages, enforced at a slice-dependent tail percentile (p99 for safety-critical URLLC slices). Organising 128 peer-reviewed studies (2017-2026) under a PRISMA 2020 protocol, we (i) map the 6G/CPS threat surface to MITRE ATT&CK and a CDR-observable feature space; (ii) unify edge anomaly detection and DDoS classification across twelve datasets and statistical, graph, and transformer models; (iii) synthesise SDN/NFV/O-RAN primitives into one closed-loop reference architecture; (iv) treat FL, large language models (LLMs), DT, post-quantum cryptography (PQC), zero-trust architecture (ZTA), and explainable AI as cross-cutting enablers, not parallel pillars; and (v) consolidate open problems into five directions spanning data, latency, trust, standardisation, and evaluation. △ Less

Submitted 6 June, 2026; originally announced June 2026.

Comments: 30 pages, 12 figures, survey paper, submitted to IEEE Communications Surveys & Tutorials (IEEE COMST)

Certified Closed-Loop Control for Packet Networks: A Compositional Certification Framework

Authors: Muhammad Bilal, Jon Crowcroft, Xiaolong Xu, Huaming Wu

Abstract: Packet networks are controlled dynamical systems with discontinuities, delayed observations, and partial state information. Adaptive or learning-driven proposers can improve performance, but an unsafe proposal may still cause starvation, tail-delay spikes, or unstable queue behaviour. This paper treats packet-network control as an executed-action certification problem. A certified operator sits be… ▽ More Packet networks are controlled dynamical systems with discontinuities, delayed observations, and partial state information. Adaptive or learning-driven proposers can improve performance, but an unsafe proposal may still cause starvation, tail-delay spikes, or unstable queue behaviour. This paper treats packet-network control as an executed-action certification problem. A certified operator sits between any proposer and the dataplane. At each control tick, the proposer emits an arbitrary candidate action $\tilde u(t)$. The operator either projects it to an executable action $u(t)$ that satisfies a configuration-compiled certificate, or reports INFEASIBLE and executes an always-defined fallback with quantified slack. The certificate also exports an auditable envelope $\bar z(t)$ for downstream composition. The guarantees are conditional and explicit. They apply on ticks where the operator reports CERTIFIED, the declared arrival envelope and backlog bound are valid, and the platform realises the assumed service lower bound. Under these conditions, one mechanism covers backlog caps, service floors, mitigation caps, Foster--Lyapunov drift constraints, and compositional envelope contracts. We prove operator-level safety, feed-forward compositional safety and stability using exported envelopes, and a cyclic closure result under a small-gain condition. We also define breach and infeasibility semantics, discuss calibration of the service-tracking factor that links certified targets to realised scheduler behaviour, and evaluate the design under delayed telemetry, delayed actuation, weak proposers, envelope mismatch, overload, and millisecond-scale certification. The present evaluation validates the certified execution boundary in a byte-level closed-loop backend; deployment-level scheduler tracking is left to future Linux or hardware experiments. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Comments: 29 pages, 11 figures, 3 tables

MSC Class: 93D15; 93D20; 90B22; 68M20 ACM Class: C.2.1; C.2.3; C.4; G.1.6

Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs

Authors: Mahdi Alkaeed, Adnan Qayyum, Nabeel Abo Kashreef, Muhammad Bilal, Junaid Qadir

Abstract: Large Language Models (LLMs) are increasingly used in clinical applications. However, their behavior remains highly sensitive to subtle linguistic variations, such as rephrasing or syntactic variation. This sensitivity poses risks in safety-critical healthcare settings, where semantically equivalent inputs should produce consistent predictions. However, a key challenge is to ensure that prompt var… ▽ More Large Language Models (LLMs) are increasingly used in clinical applications. However, their behavior remains highly sensitive to subtle linguistic variations, such as rephrasing or syntactic variation. This sensitivity poses risks in safety-critical healthcare settings, where semantically equivalent inputs should produce consistent predictions. However, a key challenge is to ensure that prompt variations truly preserve clinical meaning, as embedding-based similarity metrics often fail to capture distinctions involving negation, temporality, or severity. To address this limitation, we propose a semantic verification framework based on Natural Language Inference (NLI) to filter meaning-preserving prompt variations, which are further refined using an LLM-as-a-judge and audited by a clinical expert. In addition, we introduce three metrics to quantify model sensitivity: MeaningPreserving Variation Sensitivity (MVS), confidence variation (ΔC), and Worst-Case Instability (WCI). We evaluate 16 open-source general-purpose (GP) and medical LLMs within the same model families and parameter scales, using reformulated prompts derived from the DiagnosisQA and MedQA datasets. Our results demonstrate that robustness differences between domain-specific (DS) models are mixed and highly model-dependent, i.e., domain specialization does not consistently improve or reduce robustness to meaning-preserving prompt reformulations. Several DS models rank among the most robust (when compared with GP counterparts), and strong GP baselines remain competitive as well. △ Less

Submitted 28 May, 2026; originally announced May 2026.

Comments: 14 pages, 5 figures

PathWISE: Multi-Agent Cancer Pathway Triaging Ontology Learning from Clinical Flowcharts

Authors: Sofiat Abioye, Ufaq Khan, Shazad Ashraf, Mohammed Adil Butt, Andrew D. Beggs, Adam Byfield, Anusha Jose, Junaid Qadir, Muhammad Bilal

Abstract: Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefa… ▽ More Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefacts into validated, executable HL7 Clinical Quality Language (CQL) libraries deployable as FHIR CDS Hooks services. Purpose-built agents extract flowchart structure into a typed directed graph, perform deterministic path enumeration, conduct a structured semantic audit of every node's computability, generate terminology-constrained CQL definitions verified by the official Java CQL-to-ELM compiler, and produce routing logic covering 100% of enumerated patient journeys. Demonstrated across five UK NHS cancer pathways (colorectal, lung, skin, upper GI, and breast), PathWISE audits up to 183 nodes (182 under the Hybrid configuration), identifies 544 structured governance findings across four issue categories, achieves 100% syntactic compilation success, with UNCOMPUTABLE nodes receiving false placeholders that preserve compilability while surfacing governance gaps for clinical review, and produces zero hallucinated terminology codes for dictionary-covered concepts. Critically, PathWISE confines non-deterministic LLM inference to knowledge extraction while deterministic graph mathematics and a standard compiler underpin every verification step. △ Less

Submitted 3 June, 2026; v1 submitted 25 May, 2026; originally announced May 2026.

Comments: 13 pages, 4 figures

RAPTOR+: A Visually Grounded Vision-Language Framework to Improve Clinical Trust and Auditability in Automated Cancer Referral Processing

Authors: Sofiat Abioye, Ufaq Khan, Shazad Ashraf, Anusha Jose, Adam Byfield, Lukman Akanbi, Muhammad Bilal

Abstract: Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+,… ▽ More Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+, a multimodal extension that uses Vision-Language Models (VLMs) for end-to-end referral understanding. We evaluate fine-tuned VLMs, commercial and open-source zero-shot VLMs, and the original OCR-based pipeline on 223 clinically curated CRC urgent referral forms. We also introduce a grounding-aware evaluation framework that measures both extraction accuracy and evidence localisation. Results show a clear grounding gap in zero-shot models. Gemini 2.5 Flash achieved 92.6% Reading Accuracy but only 1.2% Strict Safety. In contrast, fine-tuned Qwen3-VL-8B achieved 96.1% Reading Accuracy and 60.6% Strict Safety, substantially improving verifiable evidence grounding. These findings show that task-specific fine-tuning is essential for reliable, auditable clinical document understanding. RAPTOR+ enables extracted referral decisions to be linked to visual evidence, supporting safer and more efficient cancer referral triage. △ Less

Submitted 3 June, 2026; v1 submitted 25 May, 2026; originally announced May 2026.

Comments: 12 pages 4 figures

Given, When, Then, Again: Mining Subscenario Refactoring Candidates in Behaviour-Driven Test Suites with ML Classifiers and LLM-Judge Baselines

Authors: Ali Hassaan Mughal, Noor Fatima, Muhammad Bilal

Abstract: Context. Behaviour-Driven Development (BDD) test suites accumulate duplicated step subsequences. Three published refactoring patterns are available (within-file Background, within-repo reusable-scenario invocation, cross-organisational shared higher-level step), but no prior work automates which recurring subsequences are worth extracting or which mechanism applies. Objective. Rank recurring step… ▽ More Context. Behaviour-Driven Development (BDD) test suites accumulate duplicated step subsequences. Three published refactoring patterns are available (within-file Background, within-repo reusable-scenario invocation, cross-organisational shared higher-level step), but no prior work automates which recurring subsequences are worth extracting or which mechanism applies. Objective. Rank recurring step subsequences ("slices") by refactoring suitability (extraction-worthy), pre-map each to one of the three patterns, and quantify prevalence across the public BDD ecosystem. Method. Every contiguous L-step window (L in [2, 18]) in a 339-repository / 276-upstream-owner Gherkin corpus is keyed by paraphrase-robust cluster identifiers and counted under three scopes. SBERT / UMAP / HDBSCAN clustering recovers paraphrase-equivalent slices. Three authors label a stratified 200-slice pool against a written rubric. An XGBoost extraction-worthy classifier trained under 5-fold cross-validation is compared with a tuned rule baseline and two open-weight Large Language Model (LLM) judges. Results. The miner produces 5,382,249 slices collapsing to 692,020 recurring patterns. Three-author Fleiss' kappa = 0.56 (extraction-worthy) and 0.79 (mechanism). The classifier reaches out-of-fold F1 = 0.891 (95% CI [0.852, 0.927]), outperforming both the rule baseline (F1 = 0.836, p = 0.017) and the better LLM judge (F1 = 0.728, p = 1.5e-4). 75.0%, 59.5%, and 11.7% of scenarios carry a within-file Background, within-repo reusable-scenario, and cross-organisational shared-step candidate, respectively; the figures are stable under a sweep of the classifier decision threshold. Conclusion. Paraphrase-robust subscenario discovery yields a corpus-wide census of BDD refactoring candidates; pipeline, classifier predictions, labelled pool, and rubric are released under Apache-2.0. △ Less

Submitted 26 June, 2026; v1 submitted 14 May, 2026; originally announced May 2026.

Comments: 31 pages, 10 figures, 6 tables, 56 references. v2: retitled; references corrected and verified; threshold-sensitivity and imbalance-robust metrics added; figures restyled. Code and data (Apache-2.0): https://github.com/amughalbscs16/cukereuse_subscenarios_release (archived: https://doi.org/10.5281/zenodo.20356527). Upstream corpus: https://doi.org/10.5281/zenodo.19754359

ACM Class: D.2.5; D.2.7; I.2.6

Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety

Authors: Muhammad Bilal, Jon Crowcroft, Ruizhi Wang, Xiaolong Xu, Schahram Dustdar

Abstract: Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited self-healing. In both NetOps and AIOps, this shift is changing how tasks are managed. Agent-based operations work as workflows, from gathering evidence to taking ac… ▽ More Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited self-healing. In both NetOps and AIOps, this shift is changing how tasks are managed. Agent-based operations work as workflows, from gathering evidence to taking action, following permissions, policies, and checks, and providing rollback options when necessary. This is crucial because operational decisions can have instant impacts. To make the argument concrete, we organise the relevant literature around the hierarchy of autonomy, tool scope, evidence traces, and assurance contracts. These contracts define what an agent may observe, propose, and execute. They also define the checks that must pass before any action is allowed. A consistent pattern appears across work on telemetry query recommendation, diagnosis, root-cause analysis, configuration synthesis, change planning, and limited self-healing. Operational reliability does not come chiefly from the model itself. It depends on the machinery around the model. We also argue that evaluation should go beyond static question answering. Agentic NetOps and AIOps systems require workflow-centred evaluation, including trace quality, bounded tool use, safe proposal generation, replay in sandboxed environments, and canary trials with rollback-aware scoring. Without these measures, a system may appear robust yet remain too fragile. Finally, we examine security, privacy, and governance risks that become acute when agents sit close to operational control surfaces. Taken together, the survey concludes that progress in intelligent NetOps and AIOps will depend on treating autonomy as a constrained operational control problem, whose outputs must be reliable, auditable, and securely deployable. △ Less

Submitted 15 June, 2026; v1 submitted 12 May, 2026; originally announced May 2026.

Comments: 49 pages, 15 figures, 6 tables; survey article

ACM Class: C.2.3; C.2.1; I.2.11; D.2.4

Deja Vu at Scale: Paraphrase-Robust Detection of Duplicate Gherkin Steps in Behaviour-Driven Software Testing with Sentence-Transformer Embeddings and a 1.1M-Step Open Benchmark

Authors: Ali Hassaan Mughal, Noor Fatima, Muhammad Bilal

Abstract: Context. Behaviour-Driven Development (BDD) suites in Gherkin accumulate step-text duplication with documented maintenance cost. Prior detectors either require runnable tests or are single-organisation, leaving a gap: a static, paraphrase-robust, step-level detector and a public benchmark to calibrate it. Objective. We release (i) the largest cross-organisational BDD step corpus to date, (… ▽ More Context. Behaviour-Driven Development (BDD) suites in Gherkin accumulate step-text duplication with documented maintenance cost. Prior detectors either require runnable tests or are single-organisation, leaving a gap: a static, paraphrase-robust, step-level detector and a public benchmark to calibrate it. Objective. We release (i) the largest cross-organisational BDD step corpus to date, (ii) a labelled pair-level calibration benchmark, and (iii) a four-strategy detector with a consolidation-savings model linking clusters to ISO/IEC 25010 maintainability sub-characteristics. Method. The corpus contains 347 public GitHub repositories, 23,667 .feature files, and 1,113,616 Gherkin steps, SPDX-tagged. The detector layers exact hashing, normalised Levenshtein, sentence-transformer cosine, and a Levenshtein-banded hybrid. Calibration uses 1,020 manually labelled step pairs under a released rubric (60-pair overlap, Fleiss kappa = 0.84). We report precision, recall, and F1 with bootstrap 95% CIs under the primary rubric and a score-free relabelling, and benchmark against SourcererCC-style and NiCad-style lexical baselines. Results. Step-weighted exact-duplicate rate is 80.2%; median-repository rate is 58.6% (Spearman rho = 0.51). The top hybrid cluster has 20,737 occurrences across 2,245 files. Near-exact reaches F1 = 0.822 on score-free labels; semantic F1 = 0.906 under the primary rubric reflects a disclosed stratification artefact. Lexical baselines reach F1 = 0.761 and 0.799. The savings model estimates 893,357 corpus-wide eliminable step occurrences; on the median repository 62.5% of step lines are eliminable. △ Less

Submitted 12 June, 2026; v1 submitted 22 April, 2026; originally announced April 2026.

Comments: 28 pages, 2 figures, 4 tables. Submitted to Information and Software Technology (Elsevier). Tool, corpus, labelled benchmark, and rubric released at https://github.com/amughalbscs16/cukereuse-release under Apache-2.0

ACM Class: D.2.5; D.2.7; I.2.7

Revisiting Code Debloating with Ground Truth-based Evaluation

Authors: Muhammad Bilal, Moiz Ali, Mohit Kumar, Fareed Zaffar, Fahad Shaon, Ashish Gehani, Sazzadur Rahaman

Abstract: Program debloating aims to remove unused code to reduce performance overhead, attack surfaces, and maintenance costs. Over time, debloating has evolved across multiple layers (container, library, and application), each building on the principles of application-level debloating. Despite its central role, application-level debloating continues to rely on imperfect proxies for measuring performance,… ▽ More Program debloating aims to remove unused code to reduce performance overhead, attack surfaces, and maintenance costs. Over time, debloating has evolved across multiple layers (container, library, and application), each building on the principles of application-level debloating. Despite its central role, application-level debloating continues to rely on imperfect proxies for measuring performance, such as test-case-driven evaluation for correctness, code size for runtime efficiency, and gadget count reduction for estimating security posture. While there is widespread skepticism about using such imperfect proxies, the community still lacks standardized methodologies or benchmarks to assess the true performance of application-level software debloating. This experience paper aims to address the gap. We revisit the foundations of application-level debloating through a ground-truth-based evaluation paradigm. Our analysis of eight state-of-the-art debloaters - Blade, Chisel, Cov, CovA, Lmcas, Trimmer, Occam, and Razor - uncovers insights previously unattainable through traditional evaluations. These tools collectively span the spectrum of source-to-source, IR-to-IR, and binary-to-binary transformation paradigms, characterizing a holistic reassessment across abstraction levels. Our analysis reveals that while dynamic analysis-based tools often remove up to 94% of code that should be retained, static analysis-based approaches exhibit the opposite behavior, showing high false retention rates due to coarse-grained dependency over-approximation. Additionally, static analyses may add code by introducing specialized variants of functions. False retentions and removals not only cause functional incorrectness but may also lead to systematic inconsistency, robustness failures, and exploitable vulnerabilities. △ Less

Submitted 21 April, 2026; v1 submitted 19 April, 2026; originally announced April 2026.

Comments: 12 pages, 3 tables, 1 figure, 17 code listings (plus 9 in appendix), Submitted to ASE 2026

MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage

Authors: Ufaq Khan, Umair Nawaz, L D M S S Teja, Numaan Saeed, Muhammad Bilal, Yutong Xie, Mohammad Yaqub, Muhammad Haris Khan

Abstract: Vision Language Models (VLMs) are increasingly used for tasks like medical report generation and visual question answering. However, fluent diagnostic text does not guarantee safe visual understanding. In clinical practice, interpretation begins with pre-diagnostic sanity checks: verifying that the input is valid to read (correct modality and anatomy, plausible viewpoint and orientation, and no ob… ▽ More Vision Language Models (VLMs) are increasingly used for tasks like medical report generation and visual question answering. However, fluent diagnostic text does not guarantee safe visual understanding. In clinical practice, interpretation begins with pre-diagnostic sanity checks: verifying that the input is valid to read (correct modality and anatomy, plausible viewpoint and orientation, and no obvious integrity violations). Existing benchmarks largely assume this step is solved, and therefore miss a critical failure mode: a model can produce plausible narratives even when the input is inconsistent or invalid. We introduce MedObvious, a 1,880-task benchmark that isolates input validation as a set-level consistency capability over small multi-panel image sets: the model must identify whether any panel violates expected coherence. MedObvious spans five progressive tiers, from basic orientation/modality mismatches to clinically motivated anatomy/viewpoint verification and triage-style cues, and includes five evaluation formats to test robustness across interfaces. Evaluating 17 different VLMs, we find that sanity checking remains unreliable: several models hallucinate anomalies on normal (negative-control) inputs, performance degrades when scaling to larger image sets, and measured accuracy varies substantially between multiple-choice and open-ended settings. These results show that pre-diagnostic verification remains unsolved for medical VLMs and should be treated as a distinct, safety-critical capability before deployment. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Comments: 11 Pages

MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding

Authors: Basit Alawode, Arif Mahmood, Muaz Khalifa Al-Radi, Shahad Albastaki, Asim Khan, Muhammad Bilal, Moshira Ali Abdalla, Mohammed Bennamoun, Sajid Javed

Abstract: Whole Slide Images (WSIs) exhibit hierarchical structure, where diagnostic information emerges from cellular morphology, regional tissue organization, and global context. Existing Computational Pathology (CPath) Multimodal Large Language Models (MLLMs) typically compress an entire WSI into a single embedding, which hinders fine-grained grounding and ignores how pathologists synthesize evidence acr… ▽ More Whole Slide Images (WSIs) exhibit hierarchical structure, where diagnostic information emerges from cellular morphology, regional tissue organization, and global context. Existing Computational Pathology (CPath) Multimodal Large Language Models (MLLMs) typically compress an entire WSI into a single embedding, which hinders fine-grained grounding and ignores how pathologists synthesize evidence across different scales. We introduce \textbf{MLLM-HWSI}, a Hierarchical WSI-level MLLM that aligns visual features with pathology language at four distinct scales, cell as word, patch as phrase, region as sentence, and WSI as paragraph to support interpretable evidence-grounded reasoning. MLLM-HWSI decomposes each WSI into multi-scale embeddings with scale-specific projectors and jointly enforces (i) a hierarchical contrastive objective and (ii) a cross-scale consistency loss, preserving semantic coherence from cells to the WSI. We compute diagnostically relevant patches and aggregate segmented cell embeddings into a compact cellular token per-patch using a lightweight \textit{Cell-Cell Attention Fusion (CCAF)} transformer. The projected multi-scale tokens are fused with text tokens and fed to an instruction-tuned LLM for open-ended reasoning, VQA, report, and caption generation tasks. Trained in three stages, MLLM-HWSI achieves new SOTA results on 13 WSI-level benchmarks across six CPath tasks. By aligning language with multi-scale visual evidence, MLLM-HWSI provides accurate, interpretable outputs that mirror diagnostic workflows and advance holistic WSI understanding. Code is available at: \href{https://github.com/BasitAlawode/HWSI-MLLM}{GitHub}. △ Less

Submitted 25 March, 2026; v1 submitted 24 March, 2026; originally announced March 2026.

AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis

Authors: Ufaq Khan, L. D. M. S. Sai Teja, Ayuba Shakiru, Mai A. Shaaban, Yutong Xie, Muhammad Bilal, Muhammad Haris Khan

Abstract: Ultrasound images vary widely across scanners, operators, and anatomical targets, which often causes models trained in one setting to generalize poorly to new hospitals and clinical conditions. The Foundation Model Challenge for Ultrasound Image Analysis (FMC-UIA) reflects this difficulty by requiring a single model to handle multiple tasks, including segmentation, detection, classification, and l… ▽ More Ultrasound images vary widely across scanners, operators, and anatomical targets, which often causes models trained in one setting to generalize poorly to new hospitals and clinical conditions. The Foundation Model Challenge for Ultrasound Image Analysis (FMC-UIA) reflects this difficulty by requiring a single model to handle multiple tasks, including segmentation, detection, classification, and landmark regression across diverse organs and datasets. We propose a unified multi-task framework based on a transformer visual encoder from the Qwen3-VL family. Intermediate token features are projected into spatial feature maps and fused using a lightweight multi-scale feature pyramid, enabling both pixel-level predictions and global reasoning within a shared representation. Each task is handled by a small task-specific prediction head, while training uses task-aware sampling and selective loss balancing to manage heterogeneous supervision and reduce task imbalance. Our method is designed to be simple to optimize and adaptable across a wide range of ultrasound analysis tasks. The performance improved from 67% to 85% on the validation set and achieved an average score of 81.84% on the official test set across all tasks. The code is publicly available at: https://github.com/saitejalekkala33/FMCUIA-ISBI.git △ Less

Submitted 19 March, 2026; originally announced March 2026.

Scalable Machines with Intrinsic Higher Mental-State Dynamics

Authors: Ahsan Adeel, M. Bilal

Abstract: Drawing on recent breakthroughs in cellular neurobiology and detailed biophysical modeling linking neocortical pyramidal neurons to distinct mental-state regimes, this work introduces a mathematically grounded formulation showing how models (e.g., Transformers) can implement computational principles underlying awake imaginative thought to pre-select relevant information before attention is applied… ▽ More Drawing on recent breakthroughs in cellular neurobiology and detailed biophysical modeling linking neocortical pyramidal neurons to distinct mental-state regimes, this work introduces a mathematically grounded formulation showing how models (e.g., Transformers) can implement computational principles underlying awake imaginative thought to pre-select relevant information before attention is applied via triadic modulation loops among queries ($Q$), keys ($K$), and values ($V$).~Scalability experiments on ImageNet-1K, benchmarked against a standard Vision Transformer (ViT), demonstrate significantly faster learning with reduced computational demand (fewer heads, layers, and tokens), consistent with our prior findings in reinforcement learning and language modeling. The approach operates at approximately $\mathcal{O}(N)$ complexity with respect to the number of input tokens $N$. △ Less

Submitted 13 March, 2026; originally announced March 2026.

An Ensemble Learning Approach towards Waste Segmentation in Cluttered Environment

Authors: Maimoona Jafar, Syed Imran Ali, Ahsan Saadat, Muhammad Bilal, Shah Khalid

Abstract: Environmental pollution is a critical global issue, with recycling emerging as one of the most viable solutions. This study focuses on waste segregation, a crucial step in recycling processes to obtain raw material. Recent advancements in computer vision have significantly contributed to waste classification and recognition. In waste segregation, segmentation masks are essential for robots to accu… ▽ More Environmental pollution is a critical global issue, with recycling emerging as one of the most viable solutions. This study focuses on waste segregation, a crucial step in recycling processes to obtain raw material. Recent advancements in computer vision have significantly contributed to waste classification and recognition. In waste segregation, segmentation masks are essential for robots to accurately localize and pick objects from conveyor belts. The complexity of real-world waste environments, characterized by deformed items without specific patterns and overlapping objects, further complicates waste segmentation tasks. This paper proposes an Ensemble Learning approach to improve segmentation accuracy by combining high performing segmentation models, U-Net and FPN, using a weighted average method. U-Net excels in capturing fine details and boundaries in segmentation tasks, while FPN effectively handles scale variation and context in complex environments, and their combined masks result in more precise predictions. The dataset used closely mimics real-life waste scenarios, and preprocessing techniques were applied to enhance feature learning for deep learning segmentation models. The ensemble model, referred to as EL-4, achieved an IoU value of 0.8306, an improvement over U-Net's 0.8065, and reduced Dice loss to 0.09019 from FPN's 0.1183. This study could contribute to the efficiency of waste sorting at Material Recovery Facility, facilitating better raw material acquisition for recycling with minimal human intervention and enhancing the overall throughput. △ Less

Submitted 14 February, 2026; originally announced February 2026.

The Alignment Bottleneck in Decomposition-Based Claim Verification

Authors: Mahmud Elahi Akhter, Federico Ruggeri, Iman Munire Bilal, Rob Procter, Maria Liakata

Abstract: Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence alignment and sub-claim error profiles. To better understand these factors, we introduce a new dataset of real-world complex claims, featuring temporally bounded e… ▽ More Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence alignment and sub-claim error profiles. To better understand these factors, we introduce a new dataset of real-world complex claims, featuring temporally bounded evidence and human-annotated sub-claim evidence spans. We evaluate decomposition under two evidence alignment setups: Sub-claim Aligned Evidence (SAE) and Repeated Claim-level Evidence (SRE). Our results reveal that decomposition brings significant performance improvement only when evidence is granular and strictly aligned. By contrast, standard setups that rely on repeated claim-level evidence (SRE) fail to improve and often degrade performance as shown across different datasets and domains (PHEMEPlus, MMM-Fact, COVID-Fact). Furthermore, we demonstrate that in the presence of noisy sub-claim labels, the nature of the error ends up determining downstream robustness. We find that conservative "abstention" significantly reduces error propagation compared to aggressive but incorrect predictions. These findings suggest that future claim decomposition frameworks must prioritize precise evidence synthesis and calibrate the label bias of sub-claim verification models. △ Less

Submitted 10 February, 2026; originally announced February 2026.

Software Testing at the Network Layer: Automated HTTP API Quality Assessment and Security Analysis of Production Web Applications

Authors: Ali Hassaan Mughal, Muhammad Bilal, Noor Fatima

Abstract: Modern web applications rely heavily on client-side API calls to fetch data, render content, and communicate with backend services. However, the quality of these network interactions (redundant requests, missing cache headers, oversized payloads, and excessive third-party dependencies) is rarely tested in a systematic way. Moreover, many of these quality deficiencies carry security implications: m… ▽ More Modern web applications rely heavily on client-side API calls to fetch data, render content, and communicate with backend services. However, the quality of these network interactions (redundant requests, missing cache headers, oversized payloads, and excessive third-party dependencies) is rarely tested in a systematic way. Moreover, many of these quality deficiencies carry security implications: missing cache headers enable cache poisoning, excessive third-party dependencies expand the supply-chain attack surface, and error responses risk leaking server internals. In this study, we present an automated software testing framework that captures and analyzes the complete HTTP traffic of 18 production websites spanning 11 categories (e-commerce, news, government, developer tools, travel, and more). Using automated browser instrumentation via Playwright, we record 108 HAR (HTTP Archive) files across 3 independent runs per page, then apply 8 heuristic-based anti-pattern detectors to produce a composite quality score (0-100) for each site. Our results reveal a wide quality spectrum: minimalist server-rendered sites achieve perfect scores of 100, while content-heavy commercial sites score as low as 56.8. We identify redundant API calls and missing cache headers as the two most pervasive anti-patterns, each affecting 67% of sites, while third-party overhead exceeds 20% on 72% of sites. One utility site makes 2,684 requests per page load, which is 447x more than the most minimal site. To protect site reputations, all identities are anonymized using category-based pseudonyms. We provide all analysis scripts, anonymized results, and reproducibility instructions as an open artifact. This work establishes an empirical baseline for HTTP API call quality across the modern web and offers a reproducible testing framework that researchers and practitioners can apply to their own applications. △ Less

Submitted 17 February, 2026; v1 submitted 8 February, 2026; originally announced February 2026.

Comments: 18+ pages, 5 figures, 3 tables. Code and data: https://github.com/amughalbscs16/network-layer-quality-testing

ACM Class: D.2.5; D.2.8; D.2.9; C.4

NOS-Gate: Queue-Aware Streaming IDS for Consumer Gateways under Timing-Controlled Evasion

Authors: Muhammad Bilal, Omer Tariq, Hasan Ahmed

Abstract: Timing and burst patterns can leak through encryption, and an adaptive adversary can exploit them. This undermines metadata-only detection in a stand-alone consumer gateway. Therefore, consumer gateways need streaming intrusion detection on encrypted traffic using metadata only, under tight CPU and latency budgets. We present a streaming IDS for stand-alone gateways that instantiates a lightweight… ▽ More Timing and burst patterns can leak through encryption, and an adaptive adversary can exploit them. This undermines metadata-only detection in a stand-alone consumer gateway. Therefore, consumer gateways need streaming intrusion detection on encrypted traffic using metadata only, under tight CPU and latency budgets. We present a streaming IDS for stand-alone gateways that instantiates a lightweight two-state unit derived from Network-Optimised Spiking (NOS) dynamics per flow, named \emph{NOS-Gate}. NOS-Gate scores fixed-length windows of metadata features and, under a $K$-of-$M$ persistence rule, triggers a reversible mitigation that temporarily reduces the flow's weight under weighted fair queueing (WFQ). We evaluate NOS-Gate under timing-controlled evasion using an executable \emph{worlds} benchmark that specifies benign device processes, auditable attacker budgets, contention structure, and packet-level WFQ replay to quantify queue impact. All methods are calibrated label-free via burn-in quantile thresholding. Across multiple reproducible worlds and malicious episodes, at an achieved $0.1\%$ false-positive operating point, NOS-Gate attains 0.952 incident recall versus 0.857 for the best baseline in these runs. Under gating, it reduces p99.9 queueing delay and p99.9 collateral delay with a mean scoring cost of $\approx 2.09\,μ\mathrm{s}$ per flow-window on CPU. △ Less

Submitted 1 June, 2026; v1 submitted 1 January, 2026; originally announced January 2026.

Comments: 9 pages, 3 figures, 4 tables. M. Bilal, O. Tariq and H. Ahmed, "NOS-Gate: Queue-Aware Streaming IDS for Consumer Gateways under Timing-Controlled Evasion," in IEEE Transactions on Consumer Electronics, doi: 10.1109/TCE.2026.3682516

MSC Class: 37N35; 60G55; 68M10; 93C10; 60K25 ACM Class: C.2.0; C.2.3; D.4.6; K.6.5; I.5.1

Toward an AI-Native Internet: Rethinking the Web Architecture for Semantic Retrieval

Authors: Muhammad Bilal, Zafar Qazi, Marco Canini

Abstract: The rise of Generative AI Search is fundamentally transforming how users and intelligent systems interact with the Internet. LLMs increasingly act as intermediaries between humans and web information. Yet the web remains optimized for human browsing rather than AI-driven semantic retrieval, resulting in wasted network bandwidth, lower information quality, and unnecessary complexity for developers.… ▽ More The rise of Generative AI Search is fundamentally transforming how users and intelligent systems interact with the Internet. LLMs increasingly act as intermediaries between humans and web information. Yet the web remains optimized for human browsing rather than AI-driven semantic retrieval, resulting in wasted network bandwidth, lower information quality, and unnecessary complexity for developers. We introduce the concept of an AI-Native Internet, a web architecture in which servers expose semantically relevant information chunks rather than full documents, supported by a Web-native semantic resolver that allows AI applications to discover relevant information sources before retrieving fine-grained chunks. Through motivational experiments, we quantify the inefficiencies of current HTML-based retrieval, and outline architectural directions and open challenges for evolving today's document-centric web into an AI-oriented substrate that better supports semantic access to web content. △ Less

Submitted 23 November, 2025; originally announced November 2025.

ACM Class: I.2; C.2.1

ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for Inertial Navigation

Authors: Omer Tariq, Muhammad Bilal, Muneeb Ul Hassan, Dongsoo Han, Jon Crowcroft

Abstract: Data-driven inertial sequence learning has revolutionized navigation in GPS-denied environments, offering superior odometric resolution compared to traditional Bayesian methods. However, deep learning-based inertial tracking systems remain vulnerable to privacy breaches that can expose sensitive training data. \hl{Existing differential privacy solutions often compromise model performance by introd… ▽ More Data-driven inertial sequence learning has revolutionized navigation in GPS-denied environments, offering superior odometric resolution compared to traditional Bayesian methods. However, deep learning-based inertial tracking systems remain vulnerable to privacy breaches that can expose sensitive training data. \hl{Existing differential privacy solutions often compromise model performance by introducing excessive noise, particularly in high-frequency inertial measurements.} In this article, we propose ConvXformer, a hybrid architecture that fuses ConvNeXt blocks with Transformer encoders in a hierarchical structure for robust inertial navigation. We propose an efficient differential privacy mechanism incorporating adaptive gradient clipping and gradient-aligned noise injection (GANI) to protect sensitive information while ensuring model performance. Our framework leverages truncated singular value decomposition for gradient processing, enabling precise control over the privacy-utility trade-off. Comprehensive performance evaluations on benchmark datasets (OxIOD, RIDI, RoNIN) demonstrate that ConvXformer surpasses state-of-the-art methods, achieving more than 40% improvement in positioning accuracy while ensuring $(ε,δ)$-differential privacy guarantees. To validate real-world performance, we introduce the Mech-IO dataset, collected from the mechanical engineering building at KAIST, where intense magnetic fields from industrial equipment induce significant sensor perturbations. This demonstrated robustness under severe environmental distortions makes our framework well-suited for secure and intelligent navigation in cyber-physical systems. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: 14 pages, 8 figures, 3 tables

MSC Class: 68T07; 68T05; 68P27; 62M10 ACM Class: I.2.6; I.5.1; I.2.9; K.4.1; K.6.5; C.3; G.3

Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals

Authors: Andrejs Sorstkins, Omer Tariq, Muhammad Bilal

Abstract: This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible environments. The framework has two complementary core mechanisms: an empirically derived transition reversibility measure called Phi of s and a, and a selective state ro… ▽ More This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible environments. The framework has two complementary core mechanisms: an empirically derived transition reversibility measure called Phi of s and a, and a selective state rollback operation. We introduce an online per state action estimator called Phi that quantifies the likelihood of returning to a prior state within a fixed horizon K. This measure is used to adjust the penalty term during temporal difference updates dynamically, integrating reversibility awareness directly into the value function. The system also includes a selective rollback operator. When an action yields an expected return markedly lower than its instantaneous estimated value and violates a predefined threshold, the agent is penalized and returns to the preceding state rather than progressing. This interrupts sub optimal high risk trajectories and avoids catastrophic steps. By combining reversibility aware evaluation with targeted rollback, the method improves safety, performance, and stability. In the CliffWalking v0 domain, the framework reduced catastrophic falls by over 99.8 percent and yielded a 55 percent increase in mean episode return. In the Taxi v3 domain, it suppressed illegal actions by greater than or equal to 99.9 percent and achieved a 65.7 percent improvement in cumulative reward, while also sharply reducing reward variance in both environments. Ablation studies confirm that the rollback mechanism is the critical component underlying these safety and performance gains, marking a robust step toward safe and reliable sequential decision making. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Comments: Submitted PLOS ONE

DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems

Authors: Alessandro Cornacchia, Vaastav Anand, Muhammad Bilal, Zafar Qazi, Marco Canini

Abstract: Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling service-oriented architectures. Yet, in the rapid evolving landscape of programming frameworks and new protocols, deploying and testing AI agents as distributed systems remains a daunting and labor-intensive task. We present D… ▽ More Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling service-oriented architectures. Yet, in the rapid evolving landscape of programming frameworks and new protocols, deploying and testing AI agents as distributed systems remains a daunting and labor-intensive task. We present DMAS-Forge, a framework designed to close this gap. DMAS-Forge decouples application logic from specific deployment choices, and aims at transparently generating the necessary glue code and configurations to spawn distributed multi-agent applications across diverse deployment scenarios with minimal manual effort. We present our vision, design principles, and a prototype of DMAS-Forge. Finally, we discuss the opportunities and future work for our approach. △ Less

Submitted 13 October, 2025; originally announced October 2025.

Comments: 1st Workshop on Systems for Agentic AI (SAA '25)

Network-Optimised Spiking Neural Network (NOS) Scheduling for 6G O-RAN: Spectral Margin and Delay-Tail Control

Authors: Muhammad Bilal, Xiaolong Xu

Abstract: This work presents a Network-Optimised Spiking (NOS) delay-aware scheduler for 6G radio access. The scheme couples a bounded two-state kernel to a clique-feasible proportional-fair (PF) grant head: the excitability state acts as a finite-buffer proxy, the recovery state suppresses repeated grants, and neighbour pressure is injected along the interference graph via delayed spikes. A small-signal an… ▽ More This work presents a Network-Optimised Spiking (NOS) delay-aware scheduler for 6G radio access. The scheme couples a bounded two-state kernel to a clique-feasible proportional-fair (PF) grant head: the excitability state acts as a finite-buffer proxy, the recovery state suppresses repeated grants, and neighbour pressure is injected along the interference graph via delayed spikes. A small-signal analysis yields a delay-dependent threshold $k_\star(Δ)$ and a spectral margin $δ= k_\star(Δ) - gHρ(W)$ that compress topology, controller gain, and delay into a single design parameter. Under light assumptions on arrivals, we prove geometric ergodicity for $δ>0$ and derive sub-Gaussian backlog and delay tail bounds with exponents proportional to $δ$. A numerical study, aligned with the analysis and a DU compute budget, compares NOS with PF and delayed backpressure (BP) across interference topologies over a $5$--$20$\,ms delay sweep. With a single gain fixed at the worst spectral radius, NOS sustains higher utilisation and a smaller 99.9th-percentile delay while remaining clique-feasible on integer PRBs. △ Less

Submitted 21 December, 2025; v1 submitted 13 October, 2025; originally announced October 2025.

Comments: 6 pages, 5 figures, 1 table

MSC Class: 68M20; 60K25; 93C23; 93D05; 90B18; 68M10; 68T07 ACM Class: C.2.1; C.2.3; C.4; I.2.6; I.6.5; G.3

Accelerating Sparse Ternary GEMM for Quantized ML on Apple Silicon

Authors: Baraq Lipshitz, Alessio Melone, Charalampos Maraziaris, Muhammed Bilal

Abstract: Sparse Ternary General Matrix-Matrix Multiplication (GEMM) remains under-optimized in existing libraries for Apple Silicon CPUs. We present a Sparse Ternary GEMM kernel optimized specifically for Apple's M-series processors. We propose a set of architecture-aware optimizations, including a novel blocked and interleaved sparse data format to improve memory locality, strategies to increase Instructi… ▽ More Sparse Ternary General Matrix-Matrix Multiplication (GEMM) remains under-optimized in existing libraries for Apple Silicon CPUs. We present a Sparse Ternary GEMM kernel optimized specifically for Apple's M-series processors. We propose a set of architecture-aware optimizations, including a novel blocked and interleaved sparse data format to improve memory locality, strategies to increase Instruction-Level Parallelism (ILP), and NEON-based Single Instruction Multiple Data (SIMD) vectorization to exploit data-level parallelism. Our scalar implementation achieves up to a 5.98x performance increase over a traditional Ternary Compressed Sparse Column (TCSC) baseline for large matrices with 50% ternary nonzero values (sparsity), reaching up to a 50.2% of the processor's theoretical peak performance, and remains stable across varying sparsity levels. Our vectorized implementation delivers up to a 5.59x performance increase for large matrices with 25% sparsity, and remains stable across varying sparsity levels. △ Less

Submitted 13 October, 2025; v1 submitted 8 October, 2025; originally announced October 2025.

Network-Optimised Spiking Neural Network for Event-Driven Networking

Authors: Muhammad Bilal

Abstract: Delay-coupled systems often require low-latency decisions from sparse telemetry, where dense fixed-step neural inference is wasteful and can degrade near stability margins. We introduce Network-Optimised Spiking (NOS), a trainable two-state event-driven dynamical unit for delayed, graph-coupled streams, whose states map to a fast load variable and a slower recovery resource. NOS uses bounded excit… ▽ More Delay-coupled systems often require low-latency decisions from sparse telemetry, where dense fixed-step neural inference is wasteful and can degrade near stability margins. We introduce Network-Optimised Spiking (NOS), a trainable two-state event-driven dynamical unit for delayed, graph-coupled streams, whose states map to a fast load variable and a slower recovery resource. NOS uses bounded excitability for finite buffers, explicit leak terms for service and damping, and graph-local coupling with per-link gates and communication delays, with differentiable resets compatible with surrogate-gradient training and neuromorphic execution. We prove existence and uniqueness of subthreshold equilibria, derive Jacobian-based stability conditions, and obtain a scalar network stability threshold that separates topology from node dynamics via a Perron-mode spectral condition. A stochastic arrival model aligned with telemetry smoothing explains increased variability as systems approach stability boundaries. On delayed graph forecasting and early-warning tasks from queue telemetry, NOS improves detection F1 and detection latency over MLP, RNN/GRU, and temporal GNN baselines under a common residual-based protocol, while providing calibration rules for resource-constrained deployments. Code and Demos: https://mbilal84.github.io/nos-snn-networking/ △ Less

Submitted 23 January, 2026; v1 submitted 27 September, 2025; originally announced September 2025.

Comments: 56 pages, 16 figures, 9 tables

MSC Class: 90B18; 60K25; 68M10; 68T07 ACM Class: C.2; C.2.1; C.4; I.2.6

Augmented Reality in Cultural Heritage: A Dual-Model Pipeline for 3D Artwork Reconstruction

Authors: Daniele Pannone, Alessia Castronovo, Maurizio Mancini, Gian Luca Foresti, Claudio Piciarelli, Rossana Gabrieli, Muhammad Yasir Bilal, Danilo Avola

Abstract: This paper presents an innovative augmented reality pipeline tailored for museum environments, aimed at recognizing artworks and generating accurate 3D models from single images. By integrating two complementary pre-trained depth estimation models, i.e., GLPN for capturing global scene structure and Depth-Anything for detailed local reconstruction, the proposed approach produces optimized depth ma… ▽ More This paper presents an innovative augmented reality pipeline tailored for museum environments, aimed at recognizing artworks and generating accurate 3D models from single images. By integrating two complementary pre-trained depth estimation models, i.e., GLPN for capturing global scene structure and Depth-Anything for detailed local reconstruction, the proposed approach produces optimized depth maps that effectively represent complex artistic features. These maps are then converted into high-quality point clouds and meshes, enabling the creation of immersive AR experiences. The methodology leverages state-of-the-art neural network architectures and advanced computer vision techniques to overcome challenges posed by irregular contours and variable textures in artworks. Experimental results demonstrate significant improvements in reconstruction accuracy and visual realism, making the system a highly robust tool for museums seeking to enhance visitor engagement through interactive digital content. △ Less

Submitted 18 July, 2025; originally announced July 2025.

Bi-GRU Based Deception Detection using EEG Signals

Authors: Danilo Avola, Muhammad Yasir Bilal, Emad Emam, Cristina Lakasz, Daniele Pannone, Amedeo Ranaldi

Abstract: Deception detection is a significant challenge in fields such as security, psychology, and forensics. This study presents a deep learning approach for classifying deceptive and truthful behavior using ElectroEncephaloGram (EEG) signals from the Bag-of-Lies dataset, a multimodal corpus designed for naturalistic, casual deception scenarios. A Bidirectional Gated Recurrent Unit (Bi-GRU) neural networ… ▽ More Deception detection is a significant challenge in fields such as security, psychology, and forensics. This study presents a deep learning approach for classifying deceptive and truthful behavior using ElectroEncephaloGram (EEG) signals from the Bag-of-Lies dataset, a multimodal corpus designed for naturalistic, casual deception scenarios. A Bidirectional Gated Recurrent Unit (Bi-GRU) neural network was trained to perform binary classification of EEG samples. The model achieved a test accuracy of 97\%, along with high precision, recall, and F1-scores across both classes. These results demonstrate the effectiveness of using bidirectional temporal modeling for EEG-based deception detection and suggest potential for real-time applications and future exploration of advanced neural architectures. △ Less

Submitted 18 July, 2025; originally announced July 2025.

Crop Pest Classification Using Deep Learning Techniques: A Review

Authors: Muhammad Hassam Ejaz, Muhammad Bilal, Usman Habib, Muhammad Attique, Tae-Sun Chung

Abstract: Insect pests continue to bring a serious threat to crop yields around the world, and traditional methods for monitoring them are often slow, manual, and difficult to scale. In recent years, deep learning has emerged as a powerful solution, with techniques like convolutional neural networks (CNNs), vision transformers (ViTs), and hybrid models gaining popularity for automating pest detection. This… ▽ More Insect pests continue to bring a serious threat to crop yields around the world, and traditional methods for monitoring them are often slow, manual, and difficult to scale. In recent years, deep learning has emerged as a powerful solution, with techniques like convolutional neural networks (CNNs), vision transformers (ViTs), and hybrid models gaining popularity for automating pest detection. This review looks at 37 carefully selected studies published between 2018 and 2025, all focused on AI-based pest classification. The selected research is organized by crop type, pest species, model architecture, dataset usage, and key technical challenges. The early studies relied heavily on CNNs but latest work is shifting toward hybrid and transformer-based models that deliver higher accuracy and better contextual understanding. Still, challenges like imbalanced datasets, difficulty in detecting small pests, limited generalizability, and deployment on edge devices remain significant hurdles. Overall, this review offers a structured overview of the field, highlights useful datasets, and outlines the key challenges and future directions for AI-based pest monitoring systems. △ Less

Submitted 8 August, 2025; v1 submitted 2 July, 2025; originally announced July 2025.

Comments: This version adds co-authors who were unintentionally left out of the prior submission. Additionally, Table 1 has been reformatted for clarity, and several typographical errors have been corrected

Autonomous Trajectory Optimization for UAVs in Disaster Zone Using Henry Gas Optimization Scheme

Authors: Zakria Qadir, Muhammad Bilal, Guoqiang Liu, Xiaolong Xu

Abstract: The unmanned aerial vehicles (UAVs) in a disaster-prone environment plays important role in assisting the rescue services and providing the internet connectivity with the outside world. However, in such a complex environment the selection of optimum trajectory of UAVs is of utmost importance. UAV trajectory optimization deals with finding the shortest path in the minimal possible time. In this pap… ▽ More The unmanned aerial vehicles (UAVs) in a disaster-prone environment plays important role in assisting the rescue services and providing the internet connectivity with the outside world. However, in such a complex environment the selection of optimum trajectory of UAVs is of utmost importance. UAV trajectory optimization deals with finding the shortest path in the minimal possible time. In this paper, a cluster optimization scheme (COS) is proposed using the Henry gas optimization (HGO) metaheuristic algorithm to identify the shortest path having minimal transportation cost and algorithm complexity. The mathematical model is designed for COS using the HGO algorithm and compared with the state-of-the-art metaheuristic algorithms such as particle swarm optimization (PSO), grey wolf optimization (GWO), cuckoo search algorithm (CSA) and barnacles mating optimizer (BMO). In order to prove the robustness of the proposed model, four different scenarios are evaluated that includes ambient environment, constrict environment, tangled environment, and complex environment. In all the aforementioned scenarios, the HGO algorithm outperforms the existing algorithms. Particularly, in the ambient environment, the HGO algorithm achieves a 39.3% reduction in transportation cost and a 16.8% reduction in computational time as compared to the PSO algorithm. Hence, the HGO algorithm can be used for autonomous trajectory optimization of UAVs in smart cities. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Comments: 12 pages, 9 figuers

ACM Class: C.2; I.6

Mobile-Driven Incentive Based Exercise for Blood Glucose Control in Type 2 Diabetes

Authors: Wasim Abbas, Hafiz Syed Muhammad Bilal, Asim Abbas, Muhammad Afzal, Je-Hoon Lee

Abstract: We propose and create an incentive based recommendation algorithm aimed at improving the lifestyle of diabetic patients. This algorithm is integrated into a real world mobile application to provide personalized health recommendations. Initially, users enter data such as step count, calorie intake, gender, age, weight, height and blood glucose levels. When the data is preprocessed, the app identifi… ▽ More We propose and create an incentive based recommendation algorithm aimed at improving the lifestyle of diabetic patients. This algorithm is integrated into a real world mobile application to provide personalized health recommendations. Initially, users enter data such as step count, calorie intake, gender, age, weight, height and blood glucose levels. When the data is preprocessed, the app identifies the personalized health and glucose management goals. The recommendation engine suggests exercise routines and dietary adjustments based on these goals. As users achieve their goals and follow these recommendations, they receive incentives, encouraging adherence and promoting positive health outcomes. Furthermore, the mobile application allows users to monitor their progress through descriptive analytics, which displays their daily activities and health metrics in graphical form. To evaluate the proposed methodology, the study was conducted with 10 participants, with type 2 diabetes for three weeks. The participants were recruited through advertisements and health expert references. The application was installed on the patient phone to use it for three weeks. The expert was also a part of this study by monitoring the patient health record. To assess the algorithm performance, we computed efficiency and proficiency. As a result, the algorithm showed proficiency and efficiency scores of 90% and 92%, respectively. Similarly, we computed user experience with application in terms of attractiveness, hedonic and pragmatic quality, involving 35 people in the study. As a result, it indicated an overall positive user response. The findings show a clear positive correlation between exercise and rewards, with noticeable improvements observed in user outcomes after exercise. △ Less

Submitted 10 April, 2025; originally announced April 2025.

Comments: This is Master thesis (submitted)

Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review

Authors: Ufaq Khan, Umair Nawaz, Adnan Qayyum, Shazad Ashraf, Yutong Xie, Muhammad Haris Khan, Muhammad Bilal, Junaid Qadir

Abstract: Recent advancements in machine learning (ML) and deep learning (DL), particularly through the introduction of Foundation Models (FMs), have significantly enhanced surgical scene understanding within minimally invasive surgery (MIS). This paper surveys the integration of state-of-the-art ML and DL technologies, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Foundati… ▽ More Recent advancements in machine learning (ML) and deep learning (DL), particularly through the introduction of Foundation Models (FMs), have significantly enhanced surgical scene understanding within minimally invasive surgery (MIS). This paper surveys the integration of state-of-the-art ML and DL technologies, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Foundation Models like the Segment Anything Model (SAM), into surgical workflows. These technologies improve segmentation accuracy, instrument tracking, and phase recognition in surgical scene understanding. The paper explores the challenges these technologies face, such as data variability and computational demands, and discusses ethical considerations and integration hurdles in clinical settings. Highlighting the roles of FMs, we bridge the technological capabilities with clinical needs and outline future research directions to enhance the adaptability, efficiency, and ethical alignment of AI applications in surgery. Our findings suggest that substantial progress has been made; however, more focused efforts are required to achieve seamless integration of these technologies into clinical workflows, ensuring they complement surgical practice by enhancing precision, reducing risks, and optimizing patient outcomes. △ Less

Submitted 3 November, 2025; v1 submitted 16 February, 2025; originally announced February 2025.

Foundation Models in Computational Pathology: A Review of Challenges, Opportunities, and Impact

Authors: Mohsin Bilal, Aadam, Manahil Raza, Youssef Altherwy, Anas Alsuhaibani, Abdulrahman Abduljabbar, Fahdah Almarshad, Paul Golding, Nasir Rajpoot

Abstract: From self-supervised, vision-only models to contrastive visual-language frameworks, computational pathology has rapidly evolved in recent years. Generative AI "co-pilots" now demonstrate the ability to mine subtle, sub-visual tissue cues across the cellular-to-pathology spectrum, generate comprehensive reports, and respond to complex user queries. The scale of data has surged dramatically, growing… ▽ More From self-supervised, vision-only models to contrastive visual-language frameworks, computational pathology has rapidly evolved in recent years. Generative AI "co-pilots" now demonstrate the ability to mine subtle, sub-visual tissue cues across the cellular-to-pathology spectrum, generate comprehensive reports, and respond to complex user queries. The scale of data has surged dramatically, growing from tens to millions of multi-gigapixel tissue images, while the number of trainable parameters in these models has risen to several billion. The critical question remains: how will this new wave of generative and multi-purpose AI transform clinical diagnostics? In this article, we explore the true potential of these innovations and their integration into clinical practice. We review the rapid progress of foundation models in pathology, clarify their applications and significance. More precisely, we examine the very definition of foundational models, identifying what makes them foundational, general, or multipurpose, and assess their impact on computational pathology. Additionally, we address the unique challenges associated with their development and evaluation. These models have demonstrated exceptional predictive and generative capabilities, but establishing global benchmarks is crucial to enhancing evaluation standards and fostering their widespread clinical adoption. In computational pathology, the broader impact of frontier AI ultimately depends on widespread adoption and societal acceptance. While direct public exposure is not strictly necessary, it remains a powerful tool for dispelling misconceptions, building trust, and securing regulatory support. △ Less

Submitted 12 February, 2025; originally announced February 2025.

Comments: 63 pages, 7 figures

TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation

Authors: Muhammad Bilal, Mahmood Alam, Deepa Bapu, Stephan Korsgen, Neeraj Lal, Simon Bach, Amir M Hajivanand, Muhammed Ali, Kamran Soomro, Iqbal Qasim, Paweł Capik, Aslam Khan, Zaheer Khan, Hunaid Vohra, Massimo Caputo, Andrew Beggs, Adnan Qayyum, Junaid Qadir, Shazad Ashraf

Abstract: Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly av… ▽ More Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly available, densely annotated surgical datasets. To address this, we present TEMSET-24K, an open-source dataset comprising 24,306 trans-anal endoscopic microsurgery (TEMS) video micro-clips. Each clip is meticulously annotated by clinical experts using a novel hierarchical labeling taxonomy encompassing phase, task, and action triplets, capturing intricate surgical workflows. To validate this dataset, we benchmarked deep learning models, including transformer-based architectures. Our in silico evaluation demonstrates high accuracy (up to 0.99) and F1 scores (up to 0.99) for key phases like Setup and Suturing. The STALNet model, tested with ConvNeXt, ViT, and SWIN V2 encoders, consistently segmented well-represented phases. TEMSET-24K provides a critical benchmark, propelling state-of-the-art solutions in surgical data science. △ Less

Submitted 10 February, 2025; originally announced February 2025.

Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription

Authors: Mahdi Alkaeed, Sofiat Abioye, Adnan Qayyum, Yosra Magdi Mekki, Ilhem Berrou, Mohamad Abdallah, Ala Al-Fuqaha, Muhammad Bilal, Junaid Qadir

Abstract: In response to the success of proprietary Large Language Models (LLMs) such as OpenAI's GPT-4, there is a growing interest in developing open, non-proprietary LLMs and AI foundation models (AIFMs) for transparent use in academic, scientific, and non-commercial applications. Despite their inability to match the refined functionalities of their proprietary counterparts, open models hold immense pote… ▽ More In response to the success of proprietary Large Language Models (LLMs) such as OpenAI's GPT-4, there is a growing interest in developing open, non-proprietary LLMs and AI foundation models (AIFMs) for transparent use in academic, scientific, and non-commercial applications. Despite their inability to match the refined functionalities of their proprietary counterparts, open models hold immense potential to revolutionize healthcare applications. In this paper, we examine the prospects of open-source LLMs and AIFMs for developing healthcare applications and make two key contributions. Firstly, we present a comprehensive survey of the current state-of-the-art open-source healthcare LLMs and AIFMs and introduce a taxonomy of these open AIFMs, categorizing their utility across various healthcare tasks. Secondly, to evaluate the general-purpose applications of open LLMs in healthcare, we present a case study on personalized prescriptions. This task is particularly significant due to its critical role in delivering tailored, patient-specific medications that can greatly improve treatment outcomes. In addition, we compare the performance of open-source models with proprietary models in settings with and without Retrieval-Augmented Generation (RAG). Our findings suggest that, although less refined, open LLMs can achieve performance comparable to proprietary models when paired with grounding techniques such as RAG. Furthermore, to highlight the clinical significance of LLMs-empowered personalized prescriptions, we perform subjective assessment through an expert clinician. We also elaborate on ethical considerations and potential risks associated with the misuse of powerful LLMs and AIFMs, highlighting the need for a cautious and responsible implementation in healthcare. △ Less

Submitted 4 February, 2025; originally announced February 2025.

Temporal Graph MLP Mixer for Spatio-Temporal Forecasting

Authors: Muhammad Bilal, Luis Carretero Lopez

Abstract: Spatiotemporal forecasting is critical in applications such as traffic prediction, climate modeling, and environmental monitoring. However, the prevalence of missing data in real-world sensor networks significantly complicates this task. In this paper, we introduce the Temporal Graph MLP-Mixer (T-GMM), a novel architecture designed to address these challenges. The model combines node-level process… ▽ More Spatiotemporal forecasting is critical in applications such as traffic prediction, climate modeling, and environmental monitoring. However, the prevalence of missing data in real-world sensor networks significantly complicates this task. In this paper, we introduce the Temporal Graph MLP-Mixer (T-GMM), a novel architecture designed to address these challenges. The model combines node-level processing with patch-level subgraph encoding to capture localized spatial dependencies while leveraging a three-dimensional MLP-Mixer to handle temporal, spatial, and feature-based dependencies. Experiments on the AQI, ENGRAD, PV-US and METR-LA datasets demonstrate the model's ability to effectively forecast even in the presence of significant missing data. While not surpassing state-of-the-art models in all scenarios, the T-GMM exhibits strong learning capabilities, particularly in capturing long-range dependencies. These results highlight its potential for robust, scalable spatiotemporal forecasting. △ Less

Submitted 17 January, 2025; originally announced January 2025.

OfficeMate: Pilot Evaluation of an Office Assistant Robot

Authors: Jiahe Pan, Sarah Schömbs, Yan Zhang, Ramtin Tabatabaei, Muhammad Bilal, Wafa Johal

Abstract: Office Assistant Robots (OARs) offer a promising solution to proactively provide in-situ support to enhance employee well-being and productivity in office spaces. We introduce OfficeMate, a social OAR designed to assist with practical tasks, foster social interaction, and promote health and well-being. Through a pilot evaluation with seven participants in an office environment, we found that users… ▽ More Office Assistant Robots (OARs) offer a promising solution to proactively provide in-situ support to enhance employee well-being and productivity in office spaces. We introduce OfficeMate, a social OAR designed to assist with practical tasks, foster social interaction, and promote health and well-being. Through a pilot evaluation with seven participants in an office environment, we found that users see potential in OARs for reducing stress and promoting healthy habits and value the robot's ability to provide companionship and physical activity reminders in the office space. However, concerns regarding privacy, communication, and the robot's interaction timing were also raised. The feedback highlights the need to carefully consider the robot's appearance and behaviour to ensure it enhances user experience and aligns with office social norms. We believe these insights will better inform the development of adaptive, intelligent OAR systems for future office space integration. △ Less

Submitted 9 January, 2025; originally announced January 2025.

Comments: 5 pages, 1 figure, accepted to HRI 2025

Machine Learning Information Retrieval and Summarisation to Support Systematic Review on Outcomes Based Contracting

Authors: Iman Munire Bilal, Zheng Fang, Miguel Arana-Catania, Felix-Anselm van Lier, Juliana Outes Velarde, Harry Bregazzi, Eleanor Carter, Mara Airoldi, Rob Procter

Abstract: As academic literature proliferates, traditional review methods are increasingly challenged by the sheer volume and diversity of available research. This article presents a study that aims to address these challenges by enhancing the efficiency and scope of systematic reviews in the social sciences through advanced machine learning (ML) and natural language processing (NLP) tools. In particular, w… ▽ More As academic literature proliferates, traditional review methods are increasingly challenged by the sheer volume and diversity of available research. This article presents a study that aims to address these challenges by enhancing the efficiency and scope of systematic reviews in the social sciences through advanced machine learning (ML) and natural language processing (NLP) tools. In particular, we focus on automating stages within the systematic reviewing process that are time-intensive and repetitive for human annotators and which lend themselves to immediate scalability through tools such as information retrieval and summarisation guided by expert advice. The article concludes with a summary of lessons learnt regarding the integrated approach towards systematic reviews and future directions for improvement, including explainability. △ Less

Submitted 11 December, 2024; originally announced December 2024.

REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecasting

Authors: Qingxiang Liu, Sheng Sun, Yuxuan Liang, Xiaolong Xu, Min Liu, Muhammad Bilal, Yuwei Wang, Xujing Li, Yu Zheng

Abstract: Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods adopt offline learning which may yield subpar performance, when concept drift occurs, i.e., distributions of historical and future data vary. Online learning can… ▽ More Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods adopt offline learning which may yield subpar performance, when concept drift occurs, i.e., distributions of historical and future data vary. Online learning can detect concept drift during model training, thus more applicable to TFF. Nevertheless, the existing federated online learning method for TFF fails to efficiently solve the concept drift problem and causes tremendous computing and communication overhead. Therefore, we propose a novel method named Resource-Efficient Federated Online Learning (REFOL) for TFF, which guarantees prediction performance in a communication-lightweight and computation-efficient way. Specifically, we design a data-driven client participation mechanism to detect the occurrence of concept drift and determine clients' participation necessity. Subsequently, we propose an adaptive online optimization strategy, which guarantees prediction performance and meanwhile avoids meaningless model updates. Then, a graph convolution-based model aggregation mechanism is designed, aiming to assess participants' contribution based on spatial correlation without importing extra communication and computing consumption on clients. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of REFOL in terms of prediction improvement and resource economization. △ Less

Submitted 21 November, 2024; originally announced November 2024.

Real-time and Downtime-tolerant Fault Diagnosis for Railway Turnout Machines (RTMs) Empowered with Cloud-Edge Pipeline Parallelism

Authors: Fan Wu, Muhammad Bilal, Haolong Xiang, Heng Wang, Jinjun Yu, Xiaolong Xu

Abstract: Railway Turnout Machines (RTMs) are mission-critical components of the railway transportation infrastructure, responsible for directing trains onto desired tracks. For safety assurance applications, especially in early-warning scenarios, RTM faults are expected to be detected as early as possible on a continuous 7x24 basis. However, limited emphasis has been placed on distributed model inference f… ▽ More Railway Turnout Machines (RTMs) are mission-critical components of the railway transportation infrastructure, responsible for directing trains onto desired tracks. For safety assurance applications, especially in early-warning scenarios, RTM faults are expected to be detected as early as possible on a continuous 7x24 basis. However, limited emphasis has been placed on distributed model inference frameworks that can meet the inference latency and reliability requirements of such mission critical fault diagnosis systems. In this paper, an edge-cloud collaborative early-warning system is proposed to enable real-time and downtime-tolerant fault diagnosis of RTMs, providing a new paradigm for the deployment of models in safety-critical scenarios. Firstly, a modular fault diagnosis model is designed specifically for distributed deployment, which utilizes a hierarchical architecture consisting of the prior knowledge module, subordinate classifiers, and a fusion layer for enhanced accuracy and parallelism. Then, a cloud-edge collaborative framework leveraging pipeline parallelism, namely CEC-PA, is developed to minimize the overhead resulting from distributed task execution and context exchange by strategically partitioning and offloading model components across cloud and edge. Additionally, an election consensus mechanism is implemented within CEC-PA to ensure system robustness during coordinator node downtime. Comparative experiments and ablation studies are conducted to validate the effectiveness of the proposed distributed fault diagnosis approach. Our ensemble-based fault diagnosis model achieves a remarkable 97.4% accuracy on a real-world dataset collected by Nanjing Metro in Jiangsu Province, China. Meanwhile, CEC-PA demonstrates superior recovery proficiency during node disruptions and speed-up ranging from 1.98x to 7.93x in total inference time compared to its counterparts. △ Less

Submitted 4 November, 2024; originally announced November 2024.

Natural Language Processing for Analyzing Electronic Health Records and Clinical Notes in Cancer Research: A Review

Authors: Muhammad Bilal, Ameer Hamza, Nadia Malik

Abstract: Objective: This review aims to analyze the application of natural language processing (NLP) techniques in cancer research using electronic health records (EHRs) and clinical notes. This review addresses gaps in the existing literature by providing a broader perspective than previous studies focused on specific cancer types or applications. Methods: A comprehensive literature search was conducted u… ▽ More Objective: This review aims to analyze the application of natural language processing (NLP) techniques in cancer research using electronic health records (EHRs) and clinical notes. This review addresses gaps in the existing literature by providing a broader perspective than previous studies focused on specific cancer types or applications. Methods: A comprehensive literature search was conducted using the Scopus database, identifying 94 relevant studies published between 2019 and 2024. Data extraction included study characteristics, cancer types, NLP methodologies, dataset information, performance metrics, challenges, and future directions. Studies were categorized based on cancer types and NLP applications. Results: The results showed a growing trend in NLP applications for cancer research, with breast, lung, and colorectal cancers being the most studied. Information extraction and text classification emerged as predominant NLP tasks. A shift from rule-based to advanced machine learning techniques, particularly transformer-based models, was observed. The Dataset sizes used in existing studies varied widely. Key challenges included the limited generalizability of proposed solutions and the need for improved integration into clinical workflows. Conclusion: NLP techniques show significant potential in analyzing EHRs and clinical notes for cancer research. However, future work should focus on improving model generalizability, enhancing robustness in handling complex clinical language, and expanding applications to understudied cancer types. Integration of NLP tools into clinical practice and addressing ethical considerations remain crucial for utilizing the full potential of NLP in enhancing cancer diagnosis, treatment, and patient outcomes. △ Less

Submitted 29 October, 2024; originally announced October 2024.

Mitigating Hallucinations Using Ensemble of Knowledge Graph and Vector Store in Large Language Models to Enhance Mental Health Support

Authors: Abdul Muqtadir, Hafiz Syed Muhammad Bilal, Ayesha Yousaf, Hafiz Farooq Ahmed, Jamil Hussain

Abstract: This research work delves into the manifestation of hallucination within Large Language Models (LLMs) and its consequential impacts on applications within the domain of mental health. The primary objective is to discern effective strategies for curtailing hallucinatory occurrences, thereby bolstering the dependability and security of LLMs in facilitating mental health interventions such as therapy… ▽ More This research work delves into the manifestation of hallucination within Large Language Models (LLMs) and its consequential impacts on applications within the domain of mental health. The primary objective is to discern effective strategies for curtailing hallucinatory occurrences, thereby bolstering the dependability and security of LLMs in facilitating mental health interventions such as therapy, counseling, and the dissemination of pertinent information. Through rigorous investigation and analysis, this study seeks to elucidate the underlying mechanisms precipitating hallucinations in LLMs and subsequently propose targeted interventions to alleviate their occurrence. By addressing this critical issue, the research endeavors to foster a more robust framework for the utilization of LLMs within mental health contexts, ensuring their efficacy and reliability in aiding therapeutic processes and delivering accurate information to individuals seeking mental health support. △ Less

Submitted 6 October, 2024; originally announced October 2024.

VEC-Sim: A Simulation Platform for Evaluating Service Caching and Computation Offloading Policies in Vehicular Edge Networks

Authors: Fan Wu, Xiaolong Xu, Muhammad Bilal, Xiangwei Wang, Hao Cheng, Siyu Wu

Abstract: Computer simulation platforms offer an alternative solution by emulating complex systems in a controlled manner. However, existing Edge Computing (EC) simulators, as well as general-purpose vehicular network simulators, are not tailored for VEC and lack dedicated support for modeling the distinct access pattern, entity mobility trajectory and other unique characteristics of VEC networks. To fill t… ▽ More Computer simulation platforms offer an alternative solution by emulating complex systems in a controlled manner. However, existing Edge Computing (EC) simulators, as well as general-purpose vehicular network simulators, are not tailored for VEC and lack dedicated support for modeling the distinct access pattern, entity mobility trajectory and other unique characteristics of VEC networks. To fill this gap, this paper proposes VEC-Sim, a versatile simulation platform for in-depth evaluation and analysis of various service caching and computation offloading policies in VEC networks. VEC-Sim incorporates realistic mechanisms to replicate real-world access patterns, including service feature vector, vehicle mobility modeling, evolving service popularity, new service upload and user preference shifts, etc. Moreover, its modular architecture and extensive Application Programming Interfaces (APIs) allow seamless integration of customized scheduling policies and user-defined metrics. A comprehensive evaluation of VEC-Sim's capabilities is undertaken in comparison to real-world ground truths. Results prove it to be accurate in reproducing classical scheduling algorithms and extremely effective in conducting case studies. △ Less

Submitted 9 October, 2024; originally announced October 2024.

Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion

Authors: Mehwish Ghafoor, Arif Mahmood, Muhammad Bilal

Abstract: In the field of 3D Human Pose Estimation from monocular videos, the presence of diverse occlusion types presents a formidable challenge. Prior research has made progress by harnessing spatial and temporal cues to infer 3D poses from 2D joint observations. This paper introduces a Dual Transformer Fusion (DTF) algorithm, a novel approach to obtain a holistic 3D pose estimation, even in the presence… ▽ More In the field of 3D Human Pose Estimation from monocular videos, the presence of diverse occlusion types presents a formidable challenge. Prior research has made progress by harnessing spatial and temporal cues to infer 3D poses from 2D joint observations. This paper introduces a Dual Transformer Fusion (DTF) algorithm, a novel approach to obtain a holistic 3D pose estimation, even in the presence of severe occlusions. Confronting the issue of occlusion-induced missing joint data, we propose a temporal interpolation-based occlusion guidance mechanism. To enable precise 3D Human Pose Estimation, our approach leverages the innovative DTF architecture, which first generates a pair of intermediate views. Each intermediate-view undergoes spatial refinement through a self-refinement schema. Subsequently, these intermediate-views are fused to yield the final 3D human pose estimation. The entire system is end-to-end trainable. Through extensive experiments conducted on the Human3.6M and MPI-INF-3DHP datasets, our method's performance is rigorously evaluated. Notably, our approach outperforms existing state-of-the-art methods on both datasets, yielding substantial improvements. The code is available here: https://github.com/MehwishG/DTF. △ Less

Submitted 6 October, 2024; originally announced October 2024.

1D-CNN-IDS: 1D CNN-based Intrusion Detection System for IIoT

Authors: Arslan Bisharat, Muhammad Mubeen, Muhammad Bilal, Saadullah Farooq Abbasi

Abstract: The demand of the Internet of Things (IoT) has witnessed exponential growth. These progresses are made possible by the technological advancements in artificial intelligence, cloud computing, and edge computing. However, these advancements exhibit multiple challenges, including cyber threats, security and privacy concerns, and the risk of potential financial losses. For this reason, this study de… ▽ More The demand of the Internet of Things (IoT) has witnessed exponential growth. These progresses are made possible by the technological advancements in artificial intelligence, cloud computing, and edge computing. However, these advancements exhibit multiple challenges, including cyber threats, security and privacy concerns, and the risk of potential financial losses. For this reason, this study developed a computationally inexpensive one-dimensional convolutional neural network (1DCNN) algorithm for cyber-attack classification. The proposed study achieved an accuracy of 99.90% to classify nine cyber-attacks. Multiple other performance metrices have been evaluated to validate the efficacy of the proposed scheme. In addition, comparison has been done with existing state-of-the-art schemes. The findings of the proposed study can significantly contribute to the development of secure intrusion detection for IIoT systems. △ Less

Submitted 13 September, 2024; originally announced September 2024.

Comments: 4 pages, 5 figures, 1 table, 29th International Conference on Automation and Computing

Intelligent Known and Novel Aircraft Recognition -- A Shift from Classification to Similarity Learning for Combat Identification

Authors: Ahmad Saeed, Haasha Bin Atif, Usman Habib, Mohsin Bilal

Abstract: Precise aircraft recognition in low-resolution remote sensing imagery is a challenging yet crucial task in aviation, especially combat identification. This research addresses this problem with a novel, scalable, and AI-driven solution. The primary hurdle in combat identification in remote sensing imagery is the accurate recognition of Novel/Unknown types of aircraft in addition to Known types. Tra… ▽ More Precise aircraft recognition in low-resolution remote sensing imagery is a challenging yet crucial task in aviation, especially combat identification. This research addresses this problem with a novel, scalable, and AI-driven solution. The primary hurdle in combat identification in remote sensing imagery is the accurate recognition of Novel/Unknown types of aircraft in addition to Known types. Traditional methods, human expert-driven combat identification and image classification, fall short in identifying Novel classes. Our methodology employs similarity learning to discern features of a broad spectrum of military and civilian aircraft. It discerns both Known and Novel aircraft types, leveraging metric learning for the identification and supervised few-shot learning for aircraft type classification. To counter the challenge of limited low-resolution remote sensing data, we propose an end-to-end framework that adapts to the diverse and versatile process of military aircraft recognition by training a generalized embedder in fully supervised manner. Comparative analysis with earlier aircraft image classification methods shows that our approach is effective for aircraft image classification (F1-score Aircraft Type of 0.861) and pioneering for quantifying the identification of Novel types (F1-score Bipartitioning of 0.936). The proposed methodology effectively addresses inherent challenges in remote sensing data, thereby setting new standards in dataset quality. The research opens new avenues for domain experts and demonstrates unique capabilities in distinguishing various aircraft types, contributing to a more robust, domain-adapted potential for real-time aircraft recognition. △ Less

Submitted 26 February, 2024; originally announced February 2024.