Fangzhou Lin

Fangzhou Lin

Research Associate at Texas A&M University

Publications

For the latest citation metrics, see my Google Scholar profile. Selected work is highlighted on the home page. My name is shown in bold below.

2026

  1. Fangzhou Lin, Yuping Wang, Yuliang Guo, Zixun Huang, Xinyu Huang, Haichong Zhang, et al. NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. Code

  2. Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee, Cho-Ying Wu, Fangzhou Lin, Hengyuan Zhang, et al. Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. Project

  3. Xiangbo Gao, Mingyang Wu, Siyuan Yang, Jiongze Yu, Parisa Taghavi, Fangzhou Lin, and Zhengzhong Tu. The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics. 1st Workshop on Video World Models: Interaction, Memory, Efficiency at CVPR, 2026.

  4. Zeyang Li, Xinyu Chen, Lingyu Jiang, Dengzhe Hou, Kazunori Yamada, Fangzhou Lin, Xiangbo Gao, and Zhengzhong Tu. Physics-Aware Video Instance Removal Benchmark. Workshop on Video Generative Models: Benchmarks and Evaluation at CVPR, 2026.

  5. Mingyang Wu, Siyuan Yang, Shuo Xing, Ashirbad Mishra, Soumik Dey, Xiangbo Gao, Jinyu Zhao, Jiongze Yu, Fangzhou Lin, et al. VGBE 2026 Challenge on Image-to-Video Consistent Generation: Methods and Results. CVPR Workshops, 2026.

  6. Lingyu Jiang, Dengzhe Hou, Yuping Wang, Yao Su, Fangzhou Lin, et al. A Compact Kolmogorov-Arnold Network Mixer for Long-Term Time Series Forecasting. Scientific Reports, 2026.

  7. Fangzhou Lin, Peiran Li, Lingyu Xu, Wenjing Chen, Qianwen Ge, Shuo Xing, et al. CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences. Under review at NeurIPS Evaluations and Datasets Track, 2026. Code

  8. Fangzhou Lin, Shuo Xing, Peiran Li, Siyuan Yang, Qianwen Ge, Kazunori Yamada, et al. CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning. Under review at NeurIPS, 2026.

  9. Lingyu Jiang, Zirui Li, Shuo Xing, Peiran Li, Tsubasa Takahashi, Dengzhe Hou, Zhengzhong Tu, Kazunori Yamada, and Fangzhou Lin. PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning. Under review at NeurIPS, 2026.

  10. Peiran Li, Fangzhou Lin, Shuo Xing, Xiang Zheng, Xi Hong, Jiashuo Sun, et al. BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature. Under review at Nature, 2026.

  11. Peiran Li, Jiashuo Sun, Fangzhou Lin, Shuo Xing, Tianfu Fu, Suofei Feng, et al. Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents. arXiv preprint, 2026.

  12. Peiran Li, Fangzhou Lin, Shuo Xing, Jiashuo Sun, Dylan Zhang, Siyuan Yang, et al. Let the Abyss Stare Back: Adaptive Falsification for Autonomous Scientific Discovery. arXiv preprint, 2026.

2025

  1. Lingyu Jiang, Yuping Wang, Yao Su, Shuo Xing, Wenjing Chen, Xin Zhang, Ziming Zhang, Fangzhou Lin, et al. KANMixer: Can KAN Serve as a New Modeling Core for Long-Term Time Series Forecasting? Under review at Transactions on Machine Learning Research (TMLR), 2025.

  2. Fangzhou Lin, Ziming Zhang, Haotian Liu, Jose Morales, Haichong Zhang, Kazunori Yamada, et al. GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching. International Conference on Learning Representations (ICLR), 2025. Project · Code

  3. Fangzhou Lin, Shang Gao, Yichuan Tang, Xihan Ma, Ryo Murakami, Ziming Zhang, et al. Spectroscopic Photoacoustic Denoising Framework Using Hybrid Analytical and Data-Free Learning Method. Photoacoustics, 44, 100729, 2025.

  4. Fangzhou Lin, Shang Gao, Yichuan Tang, Xihan Ma, Ziming Zhang, and Haichong K. Zhang. Feasibility Study of Data-Free Spectroscopic Photoacoustic Image Denoising. Medical Imaging 2025: Ultrasonic Imaging and Tomography, Vol. 13412, 134120J, SPIE, 2025.

  5. Ayaka Kubota, Shun Kodate, Yinxing Li, Fangzhou Lin, Hiroyuki Fukuda, Samy Baladram, and Kazunori D. Yamada. Learning Random Numbers to Realize Appendable Memory System for Artificial Intelligence to Acquire New Knowledge after Deployment. Interdisciplinary Information Sciences, 31(1), 1-11, 2025.

  6. Fangzhou Lin, Zilin Dai, Rigved Sanku, Songlin Hou, Kazunori D. Yamada, Haichong K. Zhang, and Ziming Zhang. A Strong View-Free Baseline Approach for Single-View Image Guided Point Cloud Completion. arXiv preprint arXiv:2506.15747, 2025.

2024

  1. Fangzhou Lin, Songlin Hou, Haotian Liu, Shang Gao, Kazunori D. Yamada, Haichong K. Zhang, and Ziming Zhang. Hyperbolic Chamfer Distance for Point Cloud Completion and Beyond. arXiv preprint arXiv:2412.17951, 2024.

  2. Fangzhou Lin, Haotian Liu, Haoying Zhou, Songlin Hou, Kazunori D. Yamada, Gregory S. Fischer, et al. Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 511-518, 2024. Oral presentation. Code

  3. Ziming Zhang, Yuping Shao, Yiqing Zhang, Fangzhou Lin, Haichong Zhang, and Elke Rundensteiner. Deep Loss Convexification for Learning Iterative Models. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024.

  4. Yun Yue, Fangzhou Lin, Guanyi Mou, and Ziming Zhang. Understanding Hyperbolic Metric Learning through Hard Negative Sampling. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.

  5. Xuechu Yu, Fangzhou Lin, Yun Yue, and Ziming Zhang. Leveraging Superfluous Information in Contrastive Representation Learning. arXiv preprint arXiv:2408.10292, 2024.

2023

  1. Fangzhou Lin, Yun Yue, Ziming Zhang, Songlin Hou, Kazunori Yamada, Vijaya Kolachalama, and Venkatesh Saligrama. InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion. Advances in Neural Information Processing Systems (NeurIPS), 2023. Code

  2. Fangzhou Lin, Yun Yue, Songlin Hou, Xuechu Yu, Yajun Xu, Kazunori D. Yamada, and Ziming Zhang. Hyperbolic Chamfer Distance for Point Cloud Completion. IEEE/CVF International Conference on Computer Vision (ICCV), 2023. Code

  3. Yun Yue, Fangzhou Lin, Kazunori D. Yamada, and Ziming Zhang. Hyperbolic Contrastive Learning. arXiv preprint arXiv:2302.01409, 2023.

2022

  1. Fangzhou Lin, Yajun Xu, Ziming Zhang, Chao Gao, and Kazunori D. Yamada. Cosmos Propagation Network: Deep Learning Model for Point Cloud Completion. Neurocomputing, 507, 221-234, 2022.

  2. Kazunori D. Yamada, Samy Baladram, and Fangzhou Lin. Relation Is an Option for Processing Context Information. Frontiers in Artificial Intelligence, 5, 924688, 2022.

  3. Chao Gao, Guanbin Cai, Xinyu Jiang, Fei Zheng, Jun Zhang, Yimin Gong, Fangzhou Lin, Xin Sun, and Xiang Bai. Conditional Feature Learning Based Transformer for Text-Based Person Search. IEEE Transactions on Image Processing, 31, 6097-6108, 2022.

  4. Yajun Xu, Shogo Arai, Daisuke Liu, Fangzhou Lin, and Kazuhiro Kosuge. FPCC: Fast Point Cloud Clustering-Based Instance Segmentation for Industrial Bin-Picking. Neurocomputing, 494, 255-268, 2022.

  5. Kazunori D. Yamada, Samy Baladram, and Fangzhou Lin. Progress in Research on Implementing Machine Consciousness. Interdisciplinary Information Sciences, 28(1), 95-105, 2022.

  6. Fangzhou Lin, Chao Gao, and Kazunori D. Yamada. An Effective Convolutional Neural Network for Visualized Understanding Transboundary Air Pollution Based on Himawari-8 Satellite Images. IEEE Geoscience and Remote Sensing Letters, 19, 1-5, 2022.

2021

  1. Kazunori D. Yamada, Fangzhou Lin, and Takashi Nakamura. Developing a Novel Recurrent Neural Network Architecture with Fewer Parameters and Good Learning Performance. Interdisciplinary Information Sciences, 27(1), 25-40, 2021.

2020

  1. Yajun Xu, Shogo Arai, Daisuke Liu, Fangzhou Lin, and Kazuhiro Kosuge. FPCC: Fast Point Cloud Clustering for Instance Segmentation. arXiv preprint arXiv:2012.14618, 2020.