arXiv subjects

Zhiwen Luo

Publications and source records attributed to Zhiwen Luo.

5 recordsLinked to original sources

arXiv2026

On the Road to Personalized Code Intelligence: Portraiting and Assisting Developers Based on Their In-IDE Behaviors

With the advent of large language models, research in automated software engineering has increasingly focused on leveraging these models to achieve a deeper semantic understanding of code or to engineer sophisticated agent-based processes. However, this research trajectory has largely overlooked a critical factor: the developers themselves. Programming is a deeply individualized activity; developers exhibit significant variation in their tool-chain preferences, domain-specific expertise, and problem-solving strategies. Consequently, the current paradigm of one-size-fits-all code intelligence systems struggles to accommodate the needs of individual developers. To address this gap, we introduce VirtualME, a novel IDE-embedded data infrastructure designed to model the developer by continuously capturing and interpreting their dynamic programming behaviors and preferences. VirtualME contains three components. (1) Log-level Behavior Extraction: it captures and extracts developers' log-level behaviors from IDE. (2) Task-level Behavior Recognition: it aggregates log-level behaviors into task-level behaviors via a multi-agent pipeline. (3) Developer-personality Measurement: it builds a rule engine to distill a four-dimensional developer persona: technology stack, ability, behavioral habits, and learning style. On top of VirtualME, we propose a solution for personalized repository-level knowledge Q&A by integrating the developer persona into the Q&A agent. We evaluated VirtualME by building a multi-repository benchmark with real-world developer trajectories, balancing correctness and personalization. Experimental results show that VirtualME-enhanced answers outperform generic baselines on five dimensions, yielding an average 33.80% improvement. Our results demonstrate that abundant, continuous developer-behavior data can pave the new way for adaptive and personalized code intelligence.

cs.SE↗

arXiv2025

Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation

Large language models (LLMs) have demonstrated impressive performance in code generation, particularly when augmented with chain-of-thought (CoT) prompting techniques. They break down requirements into intermediate reasoning steps, which act as design rationales to guide LLMs in writing code like human programmers. Thus, the quality of these steps is crucial for ensuring the correctness and reliability of the generated code. However, little is known about the quality of CoT generated by LLMs. To what extent can we trust the thoughts generated by LLMs? How good are they? This paper empirically explores the external and internal factors of why LLMs generate unsatisfactory CoTs by analyzing 1,023 failed code samples on two widely used code generation benchmarks. We also evaluate their impact on code generation performance by analyzing 210 CoT-code pairs and refining the unsatisfied CoTs by prompting LLMs. Our study reveals three key findings: (1) External factors (53.60%), such as unclear requirements and lack of context, mainly affect CoT quality, while internal factors (40.10%) stem from LLMs' misunderstanding prompts. (2) Even when CoTs are correct, 18.5% of the generated code contains errors due to instruction-following issues; conversely, 11.90% of correct code is paired with flawed CoTs. (3) Refining low-quality CoTs is feasible, i.e., LLMs improve when given detailed problem descriptions. These findings highlight key challenges in CoT-based code generation and suggest directions for improving LLM reasoning and reliability.

cs.SE↗

arXiv2023

Aligning Three-Decade Surge in Urban Cooling with Global Warming

Rising demand for space cooling has been placing enormous strain on various technological, environmental, and societal dimensions, resulting in issues related to energy consumption, environmental sustainability, health and well-being, affordability, and equity. Holistic approaches that combine energy efficiency optimization, policy-making, and societal adaptation must be rapidly promoted as viable, timely solutions. We interpret the 30-year upward trend and spikes in urban cooling demand from the perspective of climate change, urbanization, and background climates, focusing on five representative cities: Hong Kong, Sydney, Montreal, Zurich, and London. An unequivocal, worrying upward trend in cooling demand is observed in meteorological data from 1990 to 2021, using cooling degree hours (CDH) as a city-scale metric. The surge in cooling energy demand can be largely attributed to global warming, urban heat islands, and extreme heat events. Further, our quantification of the impact of the base temperature, in relation to the historical CDH, reveals that a 20% energy saving could be achieved instantly within a rather broad range of temperature and humidity by increasing the setpoint temperature by one degree, while characteristic sensational and physiological levels can be maintained at 'acceptable' and 'physiological thermal neutrality' respectively. However, the potential of reducing cooling demand can be nonlinearly and significantly lowered due to the presence of compound high relative humidity and high air temperature. To reduce cooling energy demand rapidly in a warming climate, we highlight the necessity of promoting hard and soft behavioral adaptation along with regulatory intervention for the operation of space cooling systems.

physics.soc-ph↗

arXiv2019

A stabilized second order exponential time differencing multistep method for thin film growth model without slope selection

In this paper, a stabilized second order in time accurate linear exponential time differencing (ETD) scheme for the no-slope-selection thin film growth model is presented. An artificial stabilizing term $Aτ^2\frac{\partialΔ^2 u}{\partial t}$ is added to the physical model to achieve energy stability, with ETD-based multi-step approximations and Fourier collocation spectral method applied in the time integral and spatial discretization of the evolution equation, respectively. Long time energy stability and detailed $\ell^{\infty}(0,T; \ell^2)$ error analysis are provided based on the energy method, with a careful estimate of the aliasing error. In addition, numerical experiments are presented to demonstrate the energy decay and convergence rate.

math.NA↗

arXiv2018

Dust concentration vision measurement based on moment of inertia in gray level-rank co-occurrence matrix

To improve the accuracy of existing dust concentration measurements, a dust concentration measurement based on Moment of inertia in Gray level-Rank Co-occurrence Matrix (GRCM), which is from the dust image sample measured by a machine vision system is proposed in this paper. Firstly, a Polynomial computational model between dust Concentration and Moment of inertia (PCM) is established by experimental methods and fitting methods. Then computing methods for GRCM and its Moment of inertia are constructed by theoretical and mathematical analysis methods. And then developing an on-line dust concentration vision measurement experimental system, the cement dust concentration measurement in a cement production workshop is taken as a practice example with the system and the PCM measurement. The results show that measurement error is within 9%, and the measurement range is 0.5-1000 mg/m3. Finally, comparing with the filter membrane weighing measurement, light scattering measurement and laser measurement, the proposed PCM measurement has advantages on error and cost, which can be provided a valuable reference for the dust concentration vision measurements.

cs.CV↗