Xinyuan Song

Dr. Xinyuan Song

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
27 October 2025
Verified
Conference Paper
Open access
JWJianhui Wang
Jianhui Wang
YHYangfan He
Yangfan He
YZYan Zhong
Yan Zhong
XSXinyuan Song
Xinyuan Song
JSJiayi Su
Jiayi Su
XWXueqian Wang
Xueqian Wang

29 May 2026 in Computation
Verified
Journal Article
Open access
PDF file
XCXin Liang Chia
Xin Liang Chia
PTPu Tian
Pu Tian
HYHeqi Yin
Heqi Yin
YYYao Yua
Yao Yua
AWAn-Hou Wei
An-Hou Wei
PFPengbin Feng
Pengbin Feng
This survey provides a comprehensive guide to Multimodal Large Language Models (MLLMs) with a focus on vision–language tasks, including image captioning, visual question answering, cross-modal retrieval, visual grounding, multi-image reasoning, long-video understanding, and embodied AI. We examine architectures, training pipelines, and practical applications, covering visual encoders, language model backbones, connector modules, contrastive pre-training, instruction tuning, and preference alignment. We also foreground first-principles constraints—information bottlenecks, data-processing limits, and statistical co-occurrence bias—that shape architecture, robustness, and evaluation. This survey centers on vision–language systems and does not cover audio-only models or code-generation tools without visual inputs. Through task-level analysis and system-level case studies, we examine prominent MLLM implementations while addressing key challenges in scalability, memory, energy use, inference cost, robustness, and cross-modal learning. We present a unified taxonomy of the MLLM design space, a comparative overview of representative models and evaluation benchmarks, and a discussion of open problems. Concluding with ethical considerations and responsible AI development, this survey offers theoretical frameworks and practical insights for researchers, practitioners, and students working at the intersection of natural language processing and computer vision.

12 October 2026 in ACM Computing Surveys
Verified
Journal Article
Open access
GBGuangji Bai
Guangji Bai
ZCZheng Chai
Zheng Chai
LCLing Chen
Ling Chen
SWShiyu Wang
Shiyu Wang
JLJiaying Lu
Jiaying Lu
LZLiang Zhao
Liang Zhao
The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI’s ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus—covering computational, memory, energy, financial, and network resources—and their applicability across various stages of an LLM’s lifecycle, including architecture design, pre-training, fine-tuning, and system design. Additionally, the survey introduces a nuanced categorization of resource efficiency techniques by their specific resource types, which uncovers the intricate relationships and mappings between various resources and corresponding optimization techniques. A standardized set of evaluation metrics and datasets is also presented to facilitate consistent and fair comparisons across different models and techniques. By offering a comprehensive overview of the current state-of-the-art and identifying open research avenues, this survey serves as a foundational reference for researchers and practitioners, aiding them in developing more sustainable and efficient LLMs in a rapidly evolving landscape. To make the field more accessible to interested beginners, we not only make a systematic review of existing works and a highly structured taxonomy of resource-efficient LLMs but also release a website including a constantly-updated article list https://github.com/tiingweii-shii/Awesome-Resource-Efficient-LLM-Papers.

10 November 2025
Verified
Conference Paper
Open access
LSLifan Sun
Lifan Sun
ZYZichen Yuan
Zichen Yuan
ENErsheng Ni
Ersheng Ni
WCWeihua Cheng
Weihua Cheng
XSXinyuan Song
Xinyuan Song
YLYouhua Li
Youhua Li


16 February 2026 in TechRxiv
Verified
Preprint
Open access
XSXinyuan Song
Xinyuan Song
QWQingsong Wen
Qingsong Wen
SPShirui Pan
Shirui Pan
LZLiang Zhao
Liang Zhao
Large-scale networks of agents are increasingly applied to software engineering, scientific analysis, web automation, organizational workflows, and social simulation, yet existing multi-agent architectures lack a unified framework to explain why some designs scale to long-horizon, multi-step tasks while others fail. As these systems grow, their behavior is fundamentally shaped by how agents are connected, how information is stored, and how states are updated over time. In this survey, we introduce a hierarchical taxonomy of agent systems along three core dimensions-architecture topology (centralized vs. decentralized), memory scope (global vs. local), and update behavior (static vs. dynamic)-which together induce eight system categories that organize prior work and make architectural trade-offs explicit. Using this taxonomy, we analyze how design choices influence scalability, coordination efficiency, communication overhead, planning depth, and robustness under partial failure, and we identify common failure modes and open challenges, including consistency management, agent routing, federation boundaries, and stability under noise or disruption.