Yiran Zhang

An Agentic AI and LLM-Based Framework for Probabilistic Cost Estimation from Fragmented BIM Data

Liupengfei Wu, Qian Zhang, Ruiying Xu, Yiran Zhang et autres

Building Information Modelling (BIM) has digitized construction, yet automated cost estimation still suffers from fragmented data and deterministic forecasts that ignore uncertainty. To address this gap, this study introduces a novel framework integrating agentic artificial intelligence (AI) with large language models (LLMs) …

hk, gb, nz (code pays fourni par la source)

Priority-Driven Flow Scheduling for Distributed Large Language Model Training

Tianshi Wang, Yiran Zhang, Zhang Yiao, Qiyang Zhang et autres

cn (code pays fourni par la source)

CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models

Yiran Zhang, Jin Hu, Mark Dras, Usman Naseem

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift, hallucination, overconfidence, and memory decay. Current approaches typically append full conversational histories, …

The Role of Haptic Interaction in Embodied Extended-Reality Learning: A Three-Level Meta-Analysis

Peidi Gu, Yihang Li, Hailin Ji, Yiran Zhang et autres

cn (code pays fourni par la source)

Estimation of Forest Stock Volume in Complex Terrain Using Spaceborne Lidar

Yiran Zhang, Qingtai Shu, Xiao Zhang, Zeyu Li et autres

In forest remote sensing monitoring of complex terrain, spaceborne lidar data has become a key technology for obtaining large-scale forest structure parameters due to its uniquethree-dimensional observation capabilities. However, in complex terrain conditions, there are still many challenges for spaceborne lidar. Particularly …

cn (code pays fourni par la source)

Early feature study of Yunnan pine pinewood nematode disease based on hyperspectral remote sensing of ground objects

Xiao Zhang, Yingqun Gao, L. Fu, Yiran Zhang et autres

Pine Wilt Disease (PWD), caused by the pine wood nematode, is a major global forest pathology characterized by the rapid death of pine trees within a span of three months. Forestry management policy requires the eradication of all infected trees during the …

cn (code pays fourni par la source)

Reliability-Aware Resource Allocation for Vehicular Services in Mobile Edge Computing

Lipei Yang, Sisi Li, Ao Zhou, Xiao Ma et autres

Mobile edge computing is envisioned as a promising paradigm to overcome the computational limitations of vehicles. However, current resource allocation optimizations for vehicular services in mobile edge computing are typically performed under quasi-static scenarios. Due to the time-varying wireless communication environments between …

cn (code pays fourni par la source)

The effects of a three-dimensional virtual learning medium on spatial ability and learning achievement in the anatomical sciences

Xiaoli Feng, Susan E. Powers, Lindsey E. Eberman, Zhonghua Liu et autres

cn, us (code pays fourni par la source)

ICESat-2 Performance for Terrain and Canopy Height Retrieval in Complex Mountainous Environments

Lianjin Fu, Qingtai Shu, Cuifen Xia, Zeyu Li et autres

Accurate estimation of forest canopy height and understory terrain in mountainous regions is crucial for carbon stock assessment under the Paris Agreement but remains challenging. This study aimed to evaluate ICESat-2’s performance in these complex environments. To achieve this, ICESat-2 ATL03 Version …

cn (code pays fourni par la source)

Performance Evaluation of ICESat-2 Laser Altimetry Data in Topographic and Canopy Height Retrieval Under Complex Terrain and Diverse Vegetation Conditions

Qingtai Shu, Cuifen Xia, Zeyu Li, Xiao Zhang et autres

Accurate estimation of forest canopy height and understory terrain in mountainous regions is crucial for carbon stock assessment under the Paris Agreement but remains challenging. This study aimed to evaluate ICESat-2's performance in these complex environments. To achieve this, ICESat-2 ATL03 Version …

cn (code pays fourni par la source)

Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design

Yiran Zhang, Ruiyin Li, Peng Liang, Weisong Sun et autres

Architecture design is a critical step in software development. However, creating a high-quality architecture is often costly due to the significant need for human expertise and manual effort. Recently, agents built upon Large Language Models (LLMs) have achieved remarkable success in various …

Accuracy assessment of topography and forest canopy height in complex terrain conditions of Southern China using ICESat-2 and GEDI data

L. Fu, Qingtai Shu, Zhengdao Yang, Cuifen Xia et autres

ICESat-2 and GEDI offer unique capabilities for terrain and canopy height retrievals; however, their performance and measurement precision are significantly affected by terrain conditions. Furthermore, differences in data scales complicate direct comparisons of their measurement capabilities. This study evaluates the accuracy of …

cn (code pays fourni par la source)