Publications (22)
MeTeoR: Practical Reasoning in Datalog with Metric Temporal Operators
Dingmin Wang, Pan Hu, PrzemysÅaw Andrzej WaÅÄga +1
DatalogMTL is an extension of Datalog with operators from metric temporal logic which has received significant attention in recent years. It is a highly expressive knowledge repres…
ADR: An Agentic Detection System for Enterprise Agentic AI Security
Chenning Li, Pan Hu, Justin Xu +9
We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Cont…
AnyPro: Preference-Preserving Anycast Optimization based on Strategic AS-Path Prepending
Minyuan Zhou, Yuning Chen, Jiaqi Zheng +11
Operating large-scale anycast networks is challenging because client-to-site mappings often misalign with operator's expectation due to opaque inter-domain routing. We present AnyP…
CoMoCAVs: Cohesive Decision-Guided Motion Planning for Connected and Autonomous Vehicles with Multi-Policy Reinforcement Learning
Pan Hu
Autonomous driving demands reliable and efficient solutions to closely related problems such as decision-making and motion planning. In this work, decision-making refers specifical…
SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recognition
Yang Li, Pan Hu, Yan Zhang +3
Graph Neural Networks (GNNs) have been widely used to capture spatial functional connectivity patterns to improve electroencephalography (EEG)-based depression recognition performa…
OWL2Vec*: Embedding of OWL Ontologies
Jiaoyan Chen, Pan Hu, Ernesto Jimenez-Ruiz +3
Semantic embedding of knowledge graphs has been widely studied and used for prediction and statistical analysis tasks across various domains such as Natural Language Processing and…
SegviGen: Repurposing 3D Generative Model for Part Segmentation
Lin Li, Haoran Feng, Zehuan Huang +8
We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or…
Optimised Storage for Datalog Reasoning
Xinyue Zhang, Pan Hu, Yavor Nenov +1
Materialisation facilitates Datalog reasoning by precomputing all consequences of the facts and the rules so that queries can be directly answered over the materialised facts. Howe…
Practical Reasoning in DatalogMTL
Dingmin Wang, PrzemysÅaw A. WaÅÄga, Pan Hu +1
DatalogMTL is an extension of Datalog with metric temporal operators that has found an increasing number of applications in recent years. Reasoning in DatalogMTL is, however, of hi…
Datalog Reasoning over Compressed RDF Knowledge Bases
Pan Hu, Jacopo Urbani, Boris Motik +1
Materialisation is often used in RDF systems as a preprocessing step to derive all facts implied by given RDF triples and rules. Although widely used, materialisation considers all…
Interpretable Machine Learning Model for Early Prediction of Mortality in Elderly Patients with Multiple Organ Dysfunction Syndrome (MODS): a Multicenter Retrospective Study and Cross Validation
Xiaoli Liu, Pan Hu, Zhi Mao +10
Background: Elderly patients with MODS have high risk of death and poor prognosis. The performance of current scoring systems assessing the severity of MODS and its mortality remai…
Optimised Maintenance of Datalog Materialisations
Pan Hu, Boris Motik, Ian Horrocks
To efficiently answer queries, datalog systems often materialise all consequences of a datalog program, so the materialisation must be updated whenever the input facts change. Seve…
CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation
Yifei Xu, Yuning Chen, Xumiao Zhang +8
Among the thriving ecosystem of cloud computing and the proliferation of Large Language Model (LLM)-based code generation tools, there is a lack of benchmarking for code generation…
Modular Materialisation of Datalog Programs
Pan Hu, Boris Motik, Ian Horrocks
The seminaïve algorithm can materialise all consequences of arbitrary datalog rules, and it also forms the basis for incremental algorithms that update a materialisation as the in…
Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Yilong Li, Shuai Zhang, Yijing Zeng +5
Large Multimodal Models (LMMs) are inherently modular, comprising vision and audio encoders, a projector, and a language backbone. Yet existing systems execute them monolithically,…
SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning
Jianye Xu, Pan Hu, Bassam Alrifaee
This paper introduces an open-source, decentralized framework named SigmaRL, designed to enhance both sample efficiency and generalization of multi-agent Reinforcement Learning (RL…
Goal-Driven Reasoning in DatalogMTL with Magic Sets
Shaoyu Wang, Kaiyue Zhao, Dongliang Wei +4
DatalogMTL is a powerful rule-based language for temporal reasoning. Due to its high expressive power and flexible modeling capabilities, it is suitable for a wide range of applica…
Incremental Maintenance of DatalogMTL Materialisations
Kaiyue Zhao, Dingqi Chen, Shaoyu Wang +1
DatalogMTL extends the classical Datalog language with metric temporal logic (MTL), enabling expressive reasoning over temporal data. While existing reasoning approaches, such as m…
Effects of internal asymmetry on interface curvatures and outer drags determining the oriented shift of the eccentric globules
Jingtao Wang, Genmiao Xu, Pan Hu +1
The physical mechanism of the oriented shift and inverse of eccentric globules in a modest extensional flow are investigated in this paper. Through this work, a shift of the globul…
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Yilong Li, Jingyu Liu, Hao Zhang +7
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy c…
Enhancing Datalog Reasoning with Hypertree Decompositions
Xinyue Zhang, Pan Hu, Yavor Nenov +1
Datalog reasoning based on the seminaïve evaluation strategy evaluates rules using traditional join plans, which often leads to redundancy and inefficiency in practice, especially…
Arbitrary control of the flow of light using pseudomagnetic fields in photonic crystals at telecommunication wavelengths
Pan Hu, Lu Sun, Ce Chen +5
In photonics, the idea of controlling light in a similar way that magnetic fields control electrons has always been attractive. It can be realized by synthesizing pseudomagnetic fi…