Selected work

Representative Papers

A Comparative Study of Graph Neural Network Layer Selection for Interaction Modelling in Driving Trajectory Prediction

Jun 12, 2026

Current graph neural networks (GNNs) used in autonomous driving trajectory prediction lack systematic evaluation and design guidance regarding their ability to model spatial interactions and temporal dynamics across different layers. This work systematically evaluates 19 GNN layers within a unified framework, integrating multi-head attention mechanisms with various aggregation strategies. The study reveals that sum aggregation consistently outperforms mean aggregation, and that incorporating distance-aware edge weighting alongside multi-head attention significantly enhances modeling capacity. Through extensive experiments, five superior layer combinations are identified, with ARMA, Chebyshev, and topology-aware layers consistently achieving state-of-the-art performance and substantially improving prediction accuracy. These findings lead to practical design principles for effective GNN architectures in trajectory forecasting.

0 citationsRead paper

An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques

Jul 07, 2025

This study systematically evaluates the zero-shot summarization capabilities of six large language models (LLMs) across diverse domains—including news, dialogue, and scientific literature—with emphasis on few-shot constraints and long-document challenges. To address context-length limitations, we propose a sentence-based chunking strategy enabling short-context models to process lengthy scientific papers in stages, thereby improving summary quality. Our methodology integrates zero-shot prompting, in-context learning, and dual-metric evaluation using ROUGE and BERTScore, alongside inference efficiency analysis. Results show that LLMs excel in news and dialogue summarization; the chunking strategy boosts average ROUGE-L scores for scientific literature by 12.3%; and strong interaction effects emerge among model scale, domain specificity, and prompt design. This work provides a reproducible methodology and empirical benchmark for lightweight, instruction-driven summarization systems.

0 citationsRead paper

A Novel Approach to Translate Structural Aggregation Queries to MapReduce Code

Feb 01, 2025

Efficiently mapping structured array aggregations—such as circular, grid, hierarchical, and sliding-window aggregations—in array databases (e.g., SciDB) onto MapReduce remains challenging due to semantic mismatches between array-centric operations and key-value abstractions. Method: This paper introduces the first array-semantic-aware AQL-to-MapReduce automatic translation framework. It models array-specific structural aggregations as rewriteable semantic rules, integrates aggregation-aware data partitioning, and generates multi-stage MapReduce jobs—fully supporting user-defined aggregation functions without modifying the underlying system. Contribution/Results: Experimental evaluation shows that the generated code achieves up to 10.84× speedup over manual MapReduce implementations, while guaranteeing semantic correctness and drastically reducing development complexity. The framework bridges a critical gap between high-level array query languages and distributed compilation optimizations, enabling scalable, declarative array analytics on MapReduce infrastructures.

0 citationsRead paper

Recent publications

Latest Papers

A Comparative Study of Graph Neural Network Layer Selection for Interaction Modelling in Driving Trajectory Prediction

Jun 12, 2026

Current graph neural networks (GNNs) used in autonomous driving trajectory prediction lack systematic evaluation and design guidance regarding their ability to model spatial interactions and temporal dynamics across different layers. This work systematically evaluates 19 GNN layers within a unified framework, integrating multi-head attention mechanisms with various aggregation strategies. The study reveals that sum aggregation consistently outperforms mean aggregation, and that incorporating distance-aware edge weighting alongside multi-head attention significantly enhances modeling capacity. Through extensive experiments, five superior layer combinations are identified, with ARMA, Chebyshev, and topology-aware layers consistently achieving state-of-the-art performance and substantially improving prediction accuracy. These findings lead to practical design principles for effective GNN architectures in trajectory forecasting.

0 citationsRead paper

An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques

Jul 07, 2025

This study systematically evaluates the zero-shot summarization capabilities of six large language models (LLMs) across diverse domains—including news, dialogue, and scientific literature—with emphasis on few-shot constraints and long-document challenges. To address context-length limitations, we propose a sentence-based chunking strategy enabling short-context models to process lengthy scientific papers in stages, thereby improving summary quality. Our methodology integrates zero-shot prompting, in-context learning, and dual-metric evaluation using ROUGE and BERTScore, alongside inference efficiency analysis. Results show that LLMs excel in news and dialogue summarization; the chunking strategy boosts average ROUGE-L scores for scientific literature by 12.3%; and strong interaction effects emerge among model scale, domain specificity, and prompt design. This work provides a reproducible methodology and empirical benchmark for lightweight, instruction-driven summarization systems.

0 citationsRead paper

A Novel Approach to Translate Structural Aggregation Queries to MapReduce Code

Feb 01, 2025

Efficiently mapping structured array aggregations—such as circular, grid, hierarchical, and sliding-window aggregations—in array databases (e.g., SciDB) onto MapReduce remains challenging due to semantic mismatches between array-centric operations and key-value abstractions. Method: This paper introduces the first array-semantic-aware AQL-to-MapReduce automatic translation framework. It models array-specific structural aggregations as rewriteable semantic rules, integrates aggregation-aware data partitioning, and generates multi-stage MapReduce jobs—fully supporting user-defined aggregation functions without modifying the underlying system. Contribution/Results: Experimental evaluation shows that the generated code achieves up to 10.84× speedup over manual MapReduce implementations, while guaranteeing semantic correctness and drastically reducing development complexity. The framework bridges a critical gap between high-level array query languages and distributed compilation optimizations, enabling scalable, declarative array analytics on MapReduce infrastructures.

0 citationsRead paper