Scheduled Maintenance Notice
Please note that Researcher Profiles will be undergoing scheduled maintenance on Wednesday 7th Oct, from 8:00am to 9:00am. During this time, the Researcher Profiles system will be unavailable. We apologise for any inconvenience and appreciate your understanding.
Select Publications
Preprints
, 2026, DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding, http://dx.doi.org/10.48550/arxiv.2603.06662
, 2026, TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting, http://dx.doi.org/10.48550/arxiv.2607.06349
, 2026, Do Satellites See Commuters? A Critical Benchmark of Vision Foundation Models
, 2026, Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports, http://dx.doi.org/10.48550/arxiv.2607.17122
, 2026, A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks, http://dx.doi.org/10.48550/arxiv.2607.25875
, 2026, GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation, http://dx.doi.org/10.48550/arxiv.2608.29251
, 2026, An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark, http://dx.doi.org/10.48550/arxiv.2608.27840
, 2026, Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation, http://dx.doi.org/10.48550/arxiv.2506.21599
, 2026, GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring, http://dx.doi.org/10.48550/arxiv.2605.30865
, 2026, Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins -- Dataset and Benchmarks, http://dx.doi.org/10.48550/arxiv.2505.11239
, 2026, AsyTO: Asymmetric Temporal Operator for Parameter-Efficient Multivariate Time Series Forecasting, http://dx.doi.org/10.48550/arxiv.2608.16098
, 2026, DomusFM: A Foundation Model for Event-Based Behavioral Monitoring in Smart-Homes, http://dx.doi.org/10.48550/arxiv.2602.01910
, 2026, CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning, http://dx.doi.org/10.48550/arxiv.2605.20247
, 2026, TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding, http://dx.doi.org/10.48550/arxiv.2608.00200
, 2026, StrideDiffusion: Accelerating Diffusion Models for Time-series Generation, http://dx.doi.org/10.48550/arxiv.2607.20545
, 2026, The Behavioural Reflection Test: A time-efficient measure of reflective reasoning in morally and epistemically charged decisions, http://dx.doi.org/10.48550/arxiv.2607.07961
, 2026, Engineering Carbon Credits Towards A Responsible FinTech Era: The Practices, Implications, and Future, http://dx.doi.org/10.48550/arxiv.2501.14750
, 2026, Perturbation Effects on Robustness and Individual Fairness, http://dx.doi.org/10.48550/arxiv.2404.01356
, 2026, AutoB2G: Agentic Simulation and Reinforcement Learning for Spatio-Temporal Grid-Interactive Building Control, http://dx.doi.org/10.48550/arxiv.2603.26005
, 2026, HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation, http://dx.doi.org/10.48550/arxiv.2507.00028
, 2026, ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models, http://dx.doi.org/10.48550/arxiv.2606.25800
, 2026, ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph, http://dx.doi.org/10.48550/arxiv.2606.22911
, 2026, Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks, http://dx.doi.org/10.48550/arxiv.2506.23053
, 2026, From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks, http://dx.doi.org/10.48550/arxiv.2605.29768
, 2026, Evaluating LLM Personalization via Semantic Constraint Verification, http://dx.doi.org/10.48550/arxiv.2606.16368
, 2026, Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling, http://dx.doi.org/10.48550/arxiv.2606.14047
, 2026, FOGO: Forgetting-aware Orthogonalization Optimizer, http://dx.doi.org/10.48550/arxiv.2606.10406
, 2026, An Infectious Disease Spread Simulation Based on Large Language Model Decision Making, http://dx.doi.org/10.48550/arxiv.2606.06360
, 2026, Didact: A Cross-Domain Capability Discovery System for Defence, http://dx.doi.org/10.48550/arxiv.2606.06942
, 2026, A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents, http://dx.doi.org/10.48550/arxiv.2604.17943
, 2026, AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild, http://dx.doi.org/10.48550/arxiv.2605.22715
, 2026, Long Context Modeling with Ranked Memory-Augmented Retrieval, http://dx.doi.org/10.48550/arxiv.2503.14800
, 2026, SGNO: Spectral Generator Neural Operators for Stable Long Horizon PDE Rollouts, http://dx.doi.org/10.48550/arxiv.2602.18801
, 2026, STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning, http://dx.doi.org/10.48550/arxiv.2605.10057
, 2026, DeepLévy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series, http://dx.doi.org/10.48550/arxiv.2605.10364
, 2026, MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs, http://dx.doi.org/10.48550/arxiv.2605.10064
, 2026, TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation, http://dx.doi.org/10.48550/arxiv.2605.10020
, 2026, TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding, http://dx.doi.org/10.48550/arxiv.2605.10782
, 2026, Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty, http://dx.doi.org/10.48550/arxiv.2604.10072
, 2026, CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining, https://arxiv.org/abs/2605.00933v1
, 2026, PINN-Cast: Exploring the Role of Continuous-Depth NODE in Transformers and Physics Informed Loss as Soft Physical Constraints in Short-term Weather Forecasting, http://dx.doi.org/10.48550/arxiv.2604.27313
, 2026, Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models, http://dx.doi.org/10.48550/arxiv.2604.10079
, 2026, RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA, http://dx.doi.org/10.48550/arxiv.2510.20505
, 2026, COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition, http://dx.doi.org/10.48550/arxiv.2503.07259
, 2026, SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization, http://dx.doi.org/10.48550/arxiv.2604.17351
, 2026, ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents, http://dx.doi.org/10.48550/arxiv.2508.04038
, 2026, User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation, http://dx.doi.org/10.48550/arxiv.2604.03014
, 2026, DRIFT-Net: A Spectral--Coupled Neural Operator for PDEs Learning, http://dx.doi.org/10.48550/arxiv.2509.24868
, 2026, Applying Value Sensitive Design to Location-Based Services: Designing for Shared Spaces and Local Conditions, http://dx.doi.org/10.48550/arxiv.2603.12521
, 2026, Mechanistic Indicators of Steering Effectiveness in Large Language Models, http://dx.doi.org/10.48550/arxiv.2602.01716