Zhenye Gan

Zhenye Gan

Auto-generated profile, based on publicly available information

Zhenye Gan

Tencent, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 December 2025 in Visual Intelligence
Verified
Journal Article
Open access
PDF file
YJYizhang Jin
Yizhang Jin
JLJian Li
Jian Li
TGTianjun Gu
Tianjun Gu
YLYexin Liu
Yexin Liu
BZBo Zhao
Bo Zhao
LMLizhuang Ma
Lizhuang Ma
In the past years, multimodal large language models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering and visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry. Thus, studying efficient and lightweight MLLMs has enormous potential, especially in edge computing scenarios. In this survey, we provide a comprehensive and systematic review of the current state of efficient MLLMs. Specifically, this survey summarizes the timeline of representative efficient MLLMs, the current state of research in structures and strategies, and the applications. Finally, the limitations of current efficient MLLM research and promising future directions are discussed.

29 November 2024 in The Astrophysical Journal Supplement Series
Verified
Journal Article
Open access
PWPei Wang
Pei Wang
JLJian Li
Jian Li
LJLong Ji
Long Ji
XHXian Hou
Xian Hou
EGErbil Gügercinoğlu
Erbil Gügercinoğlu
YWYidan Wang
Yidan Wang
Magnetars are neutron stars with extremely strong magnetic fields, frequently powering high-energy activity in X-rays. Pulsed radio emission following some X-ray outbursts has been detected, albeit its physical origin is unclear. It has long been speculated that the origin of magnetars’ radio signals is different from those from canonical pulsars, although convincing evidence is still lacking. Five months after magnetar SGR 1935+2154's X-ray outburst and its associated fast radio burst 20200428, a radio pulsar phase was discovered. Here we report the discovery of X-ray spectral hardening associated with the emergence of periodic radio pulsations from SGR 1935+2154 and a detailed analysis of the properties of the radio pulses. The observations suggest that radio emission originates from the outer magnetosphere of the magnetar, and the surface heating due to the bombardment of inward-going particles from the radio emission region is responsible for the observed X-ray spectral hardening.

1 March 2024 in The Astrophysical Journal Letters
Verified
Journal Article
Open access
DZD. Zhao
D. Zhao
Na WangNa Wang
Na Wang
JYJianping Yuan
Jianping Yuan
DLDi Li
Di Li
PWPei Wang
Pei Wang
CWC. J. Wang
C. J. Wang
We report the timing analysis of PSR J1846−0513, a pulsar discovered by the Five-hundred-meter Aperture Spherical radio Telescope (FAST) in Commensal Radio Astronomy FAST Survey. The pulsar possesses a spin period of 23.36 ms and a spin-down rate ( P ̇ ) of 1.0106(3) × 10−18 s s−1, and it is located in an eccentric orbit (e ∼0.208) with an orbital period of 0.61 days. The characteristic age and surface magnetic field of the pulsar are found to be 366.62 Myr and 4.9178 × 109 G, respectively, indicating that it is a recycled pulsar. Using over two years of timing data, we measure the periastron advance ω ̇ = 0.8956(8) deg yr−1. By assuming that this effect is purely relativistic, we have estimated the total mass M = 2.6287(35)M ⊙ and obtained an upper limit for the pulsar mass and a lower limit for the companion’s mass. Our results indicate that this is a double neutron star system.

6 March 2026 in Pattern Recognition
Verified
Journal Article
Closed access
WZWenbing Zhu
Wenbing Zhu
CWChengjie Wang
Chengjie Wang
BGBin-Bin Gao
Bin-Bin Gao
JZJiangning Zhang
Jiangning Zhang
GJGuannan Jiang
Guannan Jiang
LMLizhuang Ma
Lizhuang Ma

30 October 2024 in The Astrophysical Journal
Verified
Journal Article
Open access
PDF file
DZD. Zhao
D. Zhao
JYJianping Yuan
Jianping Yuan
Na WangNa Wang
Na Wang
DLDi Li
Di Li
PWPei Wang
Pei Wang
CWC. J. Wang
C. J. Wang
We present phase-connected timing ephemerides, polarization pulse profiles, and Faraday rotation measurements of 12 pulsars discovered by the Five-hundred-meter Aperture Spherical radio Telescope (FAST) in the Commensal Radio Astronomy FAST Survey. The observational data for each pulsar span at least 1 yr. Among them, PSR J1840+2843 shows subpulse drifting, and five pulsars are detected to exhibit pulse nulling phenomena. PSR J0640−0139 and PSR J2031−1254 are isolated millisecond pulsars (MSPs) with stable spin-down rates ( P ̇ ) of 4.8981(6) × 10−20 s s−1 and 6.01(2) × 10−21 s s−1, respectively. Additionally, one pulsar (PSR J1602−0611) is in a neutron star−white dwarf (WD) binary system with an 18.23-day orbit and a companion of ≤0.65 M ⊙. PSR J1602−0611 has a spin period, companion mass, and orbital eccentricity that are consistent with the theoretical expectations for MSP−helium WD (He WD) systems. Therefore, we believe that it might be an MSP−He WD binary system. The locations of PSR J1751−0542 and PSR J1840+2843 on the P − P ̇ diagram are beyond the traditional death line. This indicates that FAST has discovered some low- E ̇ pulsars, contributing new samples for testing pulsar radiation theories. We estimated the distances of these 12 pulsars based on NE2001 and YMW16 electron density models, and our work enhances the data set for investigating the electron density model of the Galaxy.

28 October 2024
Verified
Conference Paper
Open access
YJYizhang Jin
Yizhang Jin
JLJian Li
Jian Li
JZJiangning Zhang
Jiangning Zhang
JHJianlong Hu
Jianlong Hu
ZGZhenye Gan
Zhenye Gan
LMLizhuang Ma
Lizhuang Ma
Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship between two objects in an image, often neglecting world knowledge and lacking general language capabilities. In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships. Specifically, the model first constructs a visual spatial instruction-following dataset using given figure-caption pairs for the three tasks. It then employs LoRA to fine-tune a Large Language and Vision Assistant for VSD, which has 13 billion parameters and supports high-resolution images. Finally, a large language model is used to refine the generated sentences, enhancing their diversity and accuracy. LLaVA-VSD demonstrates excellent multimodal conversational capabilities and can follow open-ended instructions to assist with inquiries about object relationships in images.