Guoxin Yu 于国欣

Assistant Researcher
Peng Cheng Laboratory,
Nanshan District, Shenzhen, Guangdong, China
E-mail: yugx@pcl.ac.cn

Mobirise

About me

I am currently an Assistant Researcher at Peng Cheng Laboratory. I received my Ph.D. from the  Key Lab of Intelligent Information Processing, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS) , where I was jointly advised by Prof. Yue Yu and Prof. Xiang Ao.
My research interests center on multi-agent intelligence, efficient AI systems, and AI for code generation, with a particular focus on agent collaboration, agent memory, and adaptive routing. This is my Google Scholar.
I received my B.S. degree in Computer Science from Shandong Normal University in 2020.
From April 2022 to May 2023, I interned at the NLP Center, Tencent AI Lab, under the supervision of Dr. Lemao Liu.

Research

  • Multi-Agent Intelligence.
    Developing intelligent multi-agent systems that can collaborate effectively, retain and utilize long-term memory, and dynamically route tasks to the most suitable agents or models.
  • Efficient and Distributed AI Systems.
    Designing efficient, scalable, and distributed systems for training, serving, and coordinating AI models, with an emphasis on resource-aware computation, distributed collaboration, and reducing computational and communication overhead while maintaining strong performance.
  • AI for Code Generation.
    Building AI systems that can understand, generate, and improve code, and exploring agent-based approaches to software development and automated programming.

Publications

Peer-reviewed conference and journal publications. * denotes corresponding authorship where marked.

2026

  • LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation

    Qi Wang, Zhexu Shen, Meng Chen, Guoxin Yu*, Chaoxu Pang, Weifeng Zhao, and Wenjiang Zhou.

    ACM MM 2026 · AcceptedPaperCode
  • HGMem: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling

    Chulun Zhou, Chunkang Zhang, Guoxin Yu, Fandong Meng, Jie Zhou, Wai Lam, and Mo Yu.

    ICML 2026Paper
  • Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching

    Bo Lv, Jingbo Sun, Jianwei Lv, Chen Tang, Shaojie Zhang, Nayu Liu, Guoxin Yu, Zihao Li, Qichao Zhang, Dongbin Zhao, Ping Luo, and Yue Yu.

    ACL 2026 · Main ConferencePaper
  • GDCNet: Generative Discrepancy Comparison Network for Multimodal Sarcasm Detection

    Shuguang Zhang, Junhong Lian, Guoxin Yu, Baoxun Xu, and Xiang Ao.

    ICASSP 2026Paper
  • Fed-PISA: Federated Voice Cloning via Personalized Identity-Style Adaptation

    Qi Wang, Shituo Ma, Guoxin Yu, Hanyang Peng, and Yue Yu.

    ICASSP 2026Paper

2025

  • MIRE: A Medical Information Enhanced Framework for Long-Tail Medical Dialogue Synthesis

    Bo Lv, Chen Tang, Nayu Liu, Guoxin Yu, Xin Liu, Riyan Zhang, and Yue Yu.

    Expert Systems with Applications · 2025Paper

2024

  • Rethinking the Evaluation of In-Context Learning for LLMs

    Guoxin Yu, Lemao Liu, Mo Yu, Yue Yu, and Xiang Ao.

    EMNLP 2024 · Main ConferencePaper
  • Improving Event-Level Financial Sentiment Analysis with Retrieval-Augmented Multipath Chain-of-Thought Prompting

    Yiming Zhang, Xiang Ao, Guoxin Yu, and Qing He.

    CCF BigData 2024
  • EFSA: Towards Event-Level Financial Sentiment Analysis

    Tianyu Chen, Yiming Zhang, Guoxin Yu, Dapeng Zhang, Li Zeng, Qing He, and Xiang Ao*.

    ACL 2024 · Main ConferencePaper

2023

  • Retrieval-Augmented Few-shot Text Classification

    Guoxin Yu, Lemao Liu*, Haiyun Jiang, Shuming Shi, and Xiang Ao*.

    Findings of EMNLP 2023PaperSlidesPoster
  • Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation

    Guoxin Yu, Lemao Liu*, Haiyun Jiang, Shuming Shi, and Xiang Ao*.

    Findings of ACL 2023SlidesPoster

2021

  • Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension

    Guoxin Yu, Jiwei Li, Ling Luo, Yuxian Meng, Xiang Ao*, and Qing He.

    Findings of EMNLP 2021PaperSlides
  • Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis

    Guoxin Yu, Xiang Ao*, Ling Luo, Min Yang, Xiaofei Sun, Jiwei Li, and Qing He.

    Findings of ACL-IJCNLP 2021PaperSlides
  • Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network

    Chi Xu, Hao Feng, Guoxin Yu, Min Yang, Xiting Wang, Yan Song, and Xiang Ao*.

    DASFAA 2021PaperSlides

Honours and Awards

Recognition Award of 2022 Tencent Rhino-Bird Research Elite Program, Tencent, 2023
Tencent Rhino-Bird Research Elite Program, Tencent, 2022
First academic scholarship, ICT, CAS, 2021
Lvde's investment Master Award (虑得奖学金), ICT, CAS, 2021
Outstanding Graduate of Shandong Province, 2020
College Student Scholarship of CAS, 2019

Nobody can casually succeed,it comes from the thoroughself-control and the will.

Built with Mobirise - Click here