我目前是 西安交通大学 (XJTU) 的一名博士生，导师为 刘均 教授和 张玲玲 教授。我的研究方向主要包括 视觉推理、多模态大语言模型 (MLLMs) 和多智能体系统。

我曾于 2024 年 10 月至 2025 年 10 月期间，作为访问学生在 新加坡科技研究局 (A*STAR) 的前沿人工智能研究中心 (CFAR) 学习，导师为 Basura Fernando 教授和新加坡国立大学的 Mike Shou 教授。

我于 2021 年获得西安交通大学的计算机科学与技术学士学位，同时参与 “华为云”人工智能菁英班 项目，辅修自动化学士学位。

如果您对我的研究感兴趣，欢迎通过邮件联系我：zhang1393869716@stu.xjtu.edu.cn。

🔥 News

• 2026.04: 🎉 three papers are accepted by ACL 2026!
• 2026.02: 🎉 One paper is accepted by CVPR 2026!
• 2026.01: 🎉 One paper is accepted by CVIU 2025!
• 2025.09: 🎉 One paper is accepted by NeurIPS 2025!
• 2025.08: 🎉 One paper is accepted by EMNLP 2025!
• 2025.07: 🎉 One paper is accepted by ACM MM 2025!
• 2025.04: 🎉 One paper is accepted by ACL 2025!
• 2024.10: I start my one-year visiting at A*STAR, Singapore.
• 2024.01: 🎉 One paper is accepted by IEEE TIP 2024!
• 2023.03: 🎉 One paper is accepted by IEEE TCSVT 2023!

📝 Publications

†: Corresponding Author

📊 已发表16篇论文，其中第一作者/学生一作9篇，通讯作者2篇，第一作者CCF-A类论文6篇

📌 First-Author Publications (一作文章)

• [Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models], Xinyu Zhang, Yuxuan Dong, Lingling Zhang, Chengyou Jia, Zhuohang Dang, YiXing Yao, Yaqiang Wu, Basura Fernando, Jun Liu, CVPR 2026 (CCF-A)
• [Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving], Xinyu Zhang, Yuchen Wan, Boxuan Zhang, Zesheng Yang, Lingling Zhang, Bifan Wei, Jun Liu, ACL 2026 (CCF-A)
• [OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving], Xinyu Zhang, Boxuan Zhang, Yuchen Wan, Lingling Zhang, YiXing Yao, Bifan Wei, Yaqiang Wu, Jun Liu, ACL 2026 Findings
• CoFFT: Chain of Foresight-Focus Thought for Visual Language Models, Xinyu Zhang, Yuxuan Dong, Lingling Zhang, Chengyou Jia, Zhuohang Dang, Basura Fernando, Jun Liu, Mike Zheng Shou, NeurIPS 2025 (CCF-A)
• PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning, Xinyu Zhang, Yuxuan Dong, Yanrui Wu, Jiaxing Huang, Chengyou Jia, Basura Fernando, Mike Zheng Shou, Lingling Zhang, Jun Liu, ACL 2025 (CCF-A)
• [Cognitive Predictive Coding Network: Rethinking the Generalization in Raven’s Progressive Matrices], Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Jun Liu, ACM MM 2025 (CCF-A)
• Memory-Enriched Thought-by-Thought Framework for Complex Diagram Question Answering, Xinyu Zhang, Lingling Zhang, Yanrui Wu, Shaowei Wang, Wenjun Wu, Muye Huang, Qianying Wang and Jun Liu, CVIU 2025 (CCF-B)
• Diagram-driven course questions generation, Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, Basura Fernando, Jun Liu, EMNLP 2025 (CCF-B)
• Alignment Relation is What You Need for Diagram Parsing, Xinyu Zhang, Lingling Zhang, Xin Hu, Jun Liu, Shaowei Wang, Qianying Wang, IEEE TIP 2024 (CCF-A)

✉️ Corresponding Author Publications (通讯文章)

• [PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving], Yuxuan Dong, Xinyu Zhang†, Lingling Zhang, Han Lai, Pengyu Li, Bifan Wei, Yaqiang Wu, Jun Liu, ACL 2026 Findings
• RPMG-FSS: Robust Prior Mask Guided Few-Shot Semantic Segmentation, Lingling Zhang, Xinyu Zhang†, Qianying Wang, Wenjun Wu, Xiaojun Chang, Jun Liu, IEEE TCSVT 2023 (CCF-B)

🤝 Co-Authored Publications (合作文章)

• Correspondence Coverage Matters for Multi-Modal Dataset Distillation, Zhuohang Dang, Minnan Luo, Chengyou Jia, Hangwei Qian, Xinyu Zhang, Xiaojun Chang, Ivor Tsang, AAAI 2026 (CCF-A)
• Encode Geometric Diagram as Geo-Graph in Geometry Problem Solving, Wenjun Wu, Lingling Zhang, Bo Zhao, Bo Li, Xinyu Zhang, Yanrui Wu, AAAI 2026 (CCF-A)
• LogicGraph: Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification, Yanrui Wu, Lingling Zhang, Xinyu Zhang, Jiaqi Chang, Pengyu Li, Xiaolin Jiang, Jiancheng Hu, Jun Liu, arXiv 2026
• Evochart: A Benchmark and a Self-Training Approach towards Real-World Chart Understanding, Muye Huang, Han Lai, Xinyu Zhang, Wenjun Wu, Jie Ma, Lingling Zhang, Jun Liu, AAAI 2025 (CCF-A)
• VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning, Muye Huang, Lingling Zhang, Han Lai, Wenjun Wu, Xinyu Zhang, Jun Liu, AAAI 2025 (CCF-A)
• Cog-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering, Shaowei Wang, Lingling Zhang, Longji Zhu, Tao Qin, Kim-Hui Yap, Xinyu Zhang, Jun Liu, CVPR 2024 (CCF-A)
• Alignment-Guided Self-Supervised Learning for Diagram Question Answering, Shaowei Wang, Lingling Zhang, Wenjun Wu, Tao Qin, Xinyu Zhang, Jun Liu, IEEE TMM 2024 (CCF-A)
• Diagram Visual Grounding: Learning to See with Gestalt-Perceptual Attention, Xin Hu, Lingling Zhang, Jun Liu, Xinyu Zhang, Wenjun Wu, Qianying Wang, IJCAI 2023 (CCF-B)

🎖 Honors and Awards

• 2024-2025 西安交通大学特等奖学金、比亚迪奖学金
• 2023-2024 西安交通大学特等奖学金、优秀研究生干部
• 2019-2021 西交大-华为云菁英班奖学金
• 2020 美国大学生数学建模竞赛 特等奖提名 (Finalist)
• 2020 Intel 全国并行应用挑战赛 全国银奖
• 2019 全国大学生数学建模竞赛 国家二等奖
• 2018-2019 三星奖学金
• 2017-2018 江苏汾湖科技创新奖学金

📖 教育背景

• 2021.09 - 2026.06，博士，计算机科学与技术，西安交通大学
• 2017.08 - 2021.07，本科，计算机科学与技术，西安交通大学（辅修：自动化）

💻 研究经历

• 2024.10 - 2025.10，访问学生，新加坡科研局 (A*STAR) & 新加坡国立大学 (NUS)
• 2019.07 - 2021.07，实习生，西安交大-华为云菁英班

🎖️ 学生任职

• 2023.11 - 2024.11，主席，中国计算机学会 (CCF) 西安交通大学学生分会