Yi Xu

Research Interests

News

• Pinned Paper list of trajectory/motion prediction. Welcome to Star and Contribute! [GitHub] [Zhihu]
• Pinned Released an LLM-based trajectory prediction survey on arXiv with GitHub Repo.
• Pinned Released Awesome-Spatial-VLMs survey on TechRxiv with GitHub Repo.
• 02/2026 One paper accepted by CVPR 2026.
• 02/2026 Joined Bosch Center for Artificial Intelligence as Research Scientist.
• 02/2026 One paper on improving robustness and reliability in VLMs accepted by ICLR 2026.
• 12/2025 Successfully defended PhD thesis!
• 10/2025 One extension paper on unified trajectory imputation and prediction accepted by TPAMI.
• 08/2025 Two papers on time-series representation learning & trajectory modeling accepted by ICDM 2025; one paper on end-to-end autonomous driving + VLM accepted by CoRL 2025.
• 01/2025 One paper on unified trajectory generation accepted by ICLR 2025. [Code]
• 02/2024 Two papers accepted by CVPR 2024.
• 09/2023 One paper on adaptive optimizer design accepted by ICDM 2023; one on graph structure learning accepted by NeurIPS 2023.
• 07/2023 One paper on layout prediction accepted by ACM MM 2023.
• 05/2023 Summer internship at Honda Research Institute, San Jose, CA.
• 03/2023 Guest lecture at Northeastern University, EECE 5642.
• 02/2023 Two papers on trajectory imputation & prediction and future action localization accepted by CVPR 2023.
• 09/2022 One paper on video recognition accepted by NeurIPS 2022.
• 08/2022 One paper on video anomaly detection accepted by ICDM 2022.
• 07/2022 One paper on unsupervised anomaly detection accepted by CIKM 2022.
• 05/2022 Summer internship at Honda Research Institute, San Jose, CA.
• 04/2022 One paper on cross-domain few-shot learning accepted by IJCAI 2022.
• 03/2022 One paper on adaptive pedestrian trajectory prediction accepted by CVPR 2022.
• 09/2021 One paper on pedestrian trajectory prediction with active learning accepted by ICONIP 2021.
• 01/2021 One paper accepted by RA-L/ICRA 2021; one accepted by ACM Trans. Intell. Syst. Technol.
• 09/2020 Joined SMILE Lab as a PhD student at Northeastern University.
• 06/2020 Joined Meituan AI as summer research intern.
• 11/2019 One paper on pedestrian trajectory prediction accepted by AAAI 2020.

Education

Pre-Prints

• Yi Xu, Ruining Yang, Yitian Zhang, Yizhou Wang, Jianglin Lu, Mingyuan Zhang, Lili Su, Yun Fu, “Trajectory Prediction Meets Large Language Models: A Survey.” arXiv GitHub
• Disheng Liu, Tuo Liang, Zhe Hu, Jierui Peng, Yiren Lu, Yi Xu, Yun Fu, Yu Yin, “Spatial Intelligence in Vision-Language Models: A Comprehensive Survey.” TechRxiv GitHub

Publications

• Ruining Yang, Yi Xu, Yun Fu, Lili Su, “Den-TP: Density-Balanced Data Curation and Evaluation Framework for Trajectory Prediction.” CVPR 2026. arXiv
• Yiyang Huang, Liang Shi, Yitian Zhang, Yi Xu, Yun Fu, “SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense.” ICLR 2026. arXiv Code
• Yi Xu, Yun Fu, “Gaussian Mixture Conditional Variational Recurrent Neural Network for Unified Trajectory Imputation and Prediction.” TPAMI 2025. Paper
• Yi Xu, Yitian Zhang, Yun Fu, “MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning.” ICDM 2025. arXiv
• Yi Xu, Yun Fu, “AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports.” ICDM 2025. arXiv
• Yi Xu, Yuxin Hu, Zaiwei Zhang, Gregory P. Meyer, Siva Karthik Mustikovela, Siddhartha Srinivasa, Eric M. Wolff, Xin Huang, “VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision.” CoRL 2025. arXiv
• Yi Xu, Yun Fu, “Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports.” ICLR 2025. arXiv Code
• Yi Xu, Yun Fu, “Adapting to Length Shift: FlexiLength Network for Trajectory Prediction.” CVPR 2024. arXiv
• Haichao Zhang, Yi Xu, Hongsheng Lu, Takayuki Shimizu, Yun Fu, “Noise-free Out-of-Sight Trajectory Prediction with Vision-Positioning Denoising.” CVPR 2024.
• Jianglin Lu, Yi Xu, Huan Wang, Yue Bai, Yun Fu, “Latent Graph Inference with Limited Supervision.” NeurIPS 2023. arXiv Paper Website Code
• Haichao Zhang, Yi Xu, Hongsheng Lu, Takayuki Shimizu, Yun Fu, “Layout Sequence Prediction From Noisy Mobile Modality.” ACM MM 2023. arXiv
• Yizhou Wang, Yue Kang, Can Qin, Huan Wang, Yi Xu, Yulun Zhang, Yun Fu, “Momentum is All You Need for Data-Driven Adaptive Optimization.” ICDM 2023. arXiv Code
• Yi Xu, Armin Bazarjani, Hyung-gun Chi, Chiho Choi, Yun Fu, “Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction.” CVPR 2023. arXiv Paper Code
• Hyung-gun Chi, Kwonjoon Lee, Nakul Agarwal, Yi Xu, Karthik Ramani, Chiho Choi, “AdamsFormer for Spatial Action Localization in the Future.” CVPR 2023. Paper
• Yitian Zhang, Yue Bai, Huan Wang, Yi Xu, Yun Fu, “Look More but Care Less in Video Recognition.” NeurIPS 2022. arXiv Paper Code
• Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, Yun Fu, “Making Reconstruction-based Method Great Again for Video Anomaly Detection.” ICDM 2022. arXiv Paper Code
• Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu, Yue Bai, Yun Fu, “Self-supervision Meets Adversarial Perturbation: A Novel Framework for Anomaly Detection.” CIKM 2022. arXiv Paper Code
• Yi Xu, Lichen Wang, Yizhou Wang, Can Qin, Yulun Zhang, Yun Fu, “MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning.” IJCAI 2022. Paper
• Yi Xu, Lichen Wang, Yizhou Wang, Yun Fu, “Adaptive Trajectory Prediction via Transferable GNN.” CVPR 2022. arXiv Paper
• Yi Xu*, Dongchun Ren*, Mingxia Li, Yuehai Chen, Mingyu Fan, Huaxia Xia, “Robust Trajectory Prediction of Multiple Interacting Pedestrians via Incremental Active Learning.” ICONIP 2021. Paper
• Yanliang Zhu*, Dongchun Ren*, Yi Xu*, Deheng Qian, Mingyu Fan, Xin Li, Huaxia Xia, “Simultaneous Past and Current Social Interaction-aware Trajectory Prediction.” ACM Trans. Intell. Syst. Technol. Paper
• Yi Xu*, Dongchun Ren*, Mingxia Li, Yuehai Chen, Mingyu Fan, Huaxia Xia, “Tra2Tra: Trajectory-to-Trajectory Prediction With a Global Social Spatial-Temporal Attentive Neural Network.” IEEE RA-L / ICRA 2021. Paper
• Yi Xu*, Jing Yang*, Shaoyi Du, “CF-LSTM: Cascaded Feature-Based Long Short-Term Networks for Predicting Pedestrian Trajectory.” AAAI 2020. Paper

Experience

Teaching

• EECE 7205: Fundamentals of Computer Engineering, Spring 2023
• DS 5230: Unsupervised Machine Learning, Fall 2023
• DS 5500: Data Science Capstone, Spring 2024
• DS 5500: Data Science Capstone, Spring 2025
• DS 5220: Supervised Machine Learning and Learning Theory, Summer 2025
• CS 3000: Algorithms and Data, Fall 2025

Awards

• Northeastern PhD Network Travel Award, 2022, 2023, 2024, and 2025
• Travel Award of ICDM 2025
• Travel Award of CVPR 2022
• National Scholarship, 2018 (highest honor in China)
• Excellent Graduate Student of Xi'an Jiaotong University, 2018 and 2019
• Third Prize in the 15th China Graduate Mathematical Contest in Modeling, 2018
• Third Prize in the 4th China Graduate Future Flight Vehicle Innovation Competition, 2018

Professional Service