Hao Xu

Chao Li, Zijie Guo, Qiuting He et al.

Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks. To address this gap, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, we develop a search space with all meta-paths related to the target node type. By employing a progressive sampling algorithm, LMSPS dynamically shrinks the search space with hop-independent time complexity. Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing. Extensive experiments across diverse heterogeneous datasets validate LMSPS's capability in discovering effective long-range meta-paths, surpassing state-of-the-art methods. Our code is available at https://github.com/JHL-HUST/LMSPS.

Eric Hanchen Jiang, Haozheng Luo, Shengyuan Pang et al.

Large Language Models (LLMs) struggle with reliable mathematical reasoning, and current verification methods are often computationally expensive. This paper introduces the Energy Outcome Reward Model (EORM), a highly efficient, lightweight post-hoc verifier designed to address this challenge. EORM uses an energy-based framework to rank Chain-of-Thought (CoT) solutions, learning to distinguish correct from incorrect reasoning using only simple outcome labels, thus eliminating the need for expensive annotations. With only 55M parameters, over 127 times smaller than typical reward models, EORM boosts the accuracy of Llama 3 8B to 90.7\% on GSM8k and 63.7\% on MATH. This performance is achieved by efficiently selecting the optimal reasoning path from a pool of candidates, allowing it to match or exceed the accuracy of far more resource-intensive Best-of-N sampling techniques. Crucially, our experiments show that EORM generalizes effectively to out-of-distribution problems and unseen models, indicating it learns fundamental principles of valid reasoning. This robustness, combined with its efficiency, establishes EORM as a practical tool for deploying more dependable LLMs in complex, real-world applications.

Hao Xu

The Geofencing system is the key to operate the Unmanned Aerial Vehicle (UAV) within the safe and appropriate zone to avoid public concerns and other privacy issues. The system is designed to keep the UAV away from geofenced obstacles using the onboard GNSS and IMU location. The Geofencing system is part of the H2020 GAUSS project and facilities other subsystems, for instance, to support the command and control link, which is the security measure to secure the UAV from hijacking and signal spoofing. The regulatory authorities expressed the concern of having UAVs flying in the no-fly zone and causing troubles from offending private privacy to hazards at airport airspace. Hence the geofence system shall provide guidance message, which enables the UAV to evacuate from no-fly-zone, based on real-time updated location. This thesis aims to first illustrate the generation of geofence and then apply the geofence system on UAV operation. This application enables UAV to fly in the designated area without human intervention. The project is built with JAVA using GIS-enabled Database Management System and Open Soured Map data powered by OpenStreetMap and OS map. This method has been tested by simulations which had results of high accuracy.