arXiv subjects

Zhipeng Peng

Publications and source records attributed to Zhipeng Peng.

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↗

arXiv2023

Strong gravitational lensing of rotating regular black holes in non-minimally coupled Einstein-Yang-Mills theory

The strong gravitational lensing of a regular and rotating magnetic black hole in non-minimally coupled Einstein-Yang-Mills theory is studied. We find that, with the increase of any characteristic parameters of this black hole, such as the rotating parameter, magnetic charge and EYM parameter, the angular image position and relative magnification decrease while deflection angle and image separation increase. The results will degenerate to that of the Kerr case, R-N case with magnetic charge and Schwarzschild case when we take some specific values for the black hole parameters. The results also show that, due to the small influence of magnetic charge and Einstein-Yang-Mills parameters, it is difficult for current astronomical instruments to tell this black hole apart from a General Relativity one.

gr-qc↗

arXiv2023

Exploring differences in injury severity between occupant groups involved in fatal rear-end crashes: A correlated random parameter logit model with mean heterogeneity

Rear-end crashes are one of the most common crash types. Passenger cars involved in rear-end crashes frequently produce severe outcomes. However, no study investigated the differences in the injury severity of occupant groups when cars are involved as following and leading vehicles in rear-end crashes. Therefore, the focus of this investigation is to compare the key factors affecting the injury severity between the front- and rear-car occupant groups in rear-end crashes. First, data is extracted from the Fatality Analysis Reporting System (FARS) for two types of rear-end crashes from 2017 to 2019, including passenger cars as rear-end and rear-ended vehicles. Significant injury severity difference between front- and rear-car occupant groups is found by conducting likelihood ratio test. Moreover, the front- and rear-car occupant groups are modelled by the correlated random parameter logit model with heterogeneity in means (CRPLHM) and the random parameter logit model with heterogeneity in means (RPLHM), respectively. From the modeling, the significant factors are occupant positions, driver age, overturn, vehicle type, etc. For instance, the driving and front-right positions significantly increase the probability of severe injury when struck by another vehicle. Large truck-strike-car tends to cause severe outcomes compared to car-strike-large truck. This study provides an insightful knowledge of mechanism of occupant injury severity in rear-end crashes, and propose some effective countermeasures to mitigate the crash severity, such as implementing stricter seat belt laws, improving the coverage of the streetlights, strengthening car driver's emergency response ability.

stat.AP↗

arXiv2019

Relativistic Mean Motion Resonance

Mean motion resonances are commonly seen in planetary systems, e.g., in the formation of orbital structure of Jupiter's moons and the gaps in the rings of Saturn. In this work we study their effects in fully relativistic systems. We consider a model problem with two stellar mass black holes orbiting around a supermassive black hole. By adopting a two time-scale expansion technique and averaging over the fast varying orbital variables, we derive the effective Hamiltonian for the slowly varying dynamical variables. The formalism is illustrated with a n'_phi : n'_r : n_phi= 2:1:-2 resonance in Schwarzschild spacetime, which naturally becomes the 3:2 resonance widely studied in the Newtonian limit. We also derive the multi-body Hamiltonian in the post-Newtonian regime, where the radial and azimuthal frequencies are different because of the post-Newtonian precession. The capture and breaking conditions for these relativistic mean motion resonances are also discussed. In particular, pairs of stellar mass black holes surrounding the supermassive black hole could be locked into resonances as they enter the LISA band, and this would affect their gravitational wave waveforms.

gr-qc↗

arXiv2017

Compactness of solutions to nonlocal elliptic equations

We show that all nonnegative solutions of the critical semilinear elliptic equation involving the regional fractional Laplacian are locally universally bounded. This strongly contrasts with the standard fractional Laplacian case. Second, we consider the fractional critical elliptic equations with nonnegative potentials. We prove compactness of solutions provided the potentials only have non-degenerate zeros. Corresponding to Schoen's Weyl tensor vanishing conjecture for the Yamabe equation on manifolds, we establish a Laplacian vanishing rate of the potentials at blow-up points of solutions.

math.AP↗