publications

publications by categories in reversed chronological order. * equal contribution; # corresponding author.

2026

  1. Arxiv
    VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
    Mingkang Dong, Hongyi Cai, Jie Li, and 4 more authors
    arXiv preprint arXiv:2603.01195, 2026
    PDF
  2. CVPR 2026
    Yo’City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
    Keyang Lu, Sifan Zhou, Hongbin Xu, and 6 more authors
    arXiv preprint arXiv:2511.18734, 2026
    PDF
  3. ICLR 2026
    UniF^2ace: A Unified Fine-grained Face Understanding and Generation Model
    Junzhe Li*, Sifan Zhou*, Guo Liya, and 8 more authors
    In The Fourteenth International Conference on Learning Representations, 2026
    PDF
  4. ICRA 2026
    Gsrender: Deduplicated occupancy prediction via weakly supervised 3d gaussian splatting
    Qianpu Sun*, Sifan Zhou*, Changyong Shu, and 6 more authors
    2026 IEEE International Conference on Robotics and Automation (ICRA), 2026
    PDF
  5. R-AL 2026
    Beyond Frame-wise Tracking: A Trajectory-Based Paradigm for Efficient Point Cloud Tracking
    BaiChen Fan*, Sifan Zhou*#, Jian Li, and 3 more authors
    IEEE Robotics and Automation Letters, 2026
    PDF Video Code
  6. AAAI (Oral)
    CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking
    Sifan Zhou, Cao Yichao, Nie Jiahao, and 4 more authors
    In The Fortieth AAAI Conference on Artificial Intelligence (Oral), 2026
    PDF
  7. AAAI 2026
    FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection
    Jiangyong Yu, Shu Changyong, Sifan Zhou, and 4 more authors
    In The Fortieth AAAI Conference on Artificial Intelligenc, 2026
    PDF

2025

  1. Science Robotics
    Resilient Odometry via Hierarchical Adaptation
    Shibo Zhao, Sifan Zhou, Zhang Yuchen, and 4 more authors
    Science Robotics, 2025
    PDF Video Code Website
  2. TCSVT
    FastPillars: A Deployment-friendly Pillar-based 3D Detector
    Sifan Zhou, Xinyu Zhang, Xiangxiang Chu, and 3 more authors
    In IEEE Transactions on Circuits and Systems for Video Technology, 2025
    PDF Code
  3. CVPR 2025
    Pillarhist: A quantization-aware pillar feature encoder based on height-aware histogram
    Sifan Zhou*, Zhihang Yuan*, Dawei Yang, and 3 more authors
    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025
    PDF
  4. CVPR 2025
    Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics
    Shibo Zhao*, Sifan Zhou*, Raphael Blanchard, and 3 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    PDF Code Website
  5. ACM MM
    Focus Track: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking
    Sifan Zhou, Nie Jiahao, Zhao Ziyu, and 2 more authors
    In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2025
    PDF
  6. ACM MM
    MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization
    Jiangyong Yu*, Sifan Zhou*, Yang Dawei, and 7 more authors
    In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2025
    PDF Code
  7. ACL (Findings)
    GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
    Sifan Zhou*, Shuo Wang*, Zhihang Yuan*, and 3 more authors
    In Findings of the Association for Computational Linguistics: ACL 2025, Jul 2025
    PDF
  8. NeurIPS 2025
    Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
    Jianyu Wang, Yu Wang, Shengjie Zhao, and 1 more author
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
    PDF
  9. IJCV
    P2p: Part-to-part motion cues guide a strong tracking framework for lidar point clouds
    Jiahao Nie, Fei Xie, Sifan Zhou, and 3 more authors
    International Journal of Computer Vision, 2025
    PDF Code
  10. ICRA 2025
    Mvctrack: Boosting 3d point cloud tracking via multimodal-guided virtual cues
    Zhaofeng Hu, Sifan Zhou*#, Zhihang Yuan, and 3 more authors
    In 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
    PDF Video Code
  11. ICRA 2025
    Ptq4ris: Post-training quantization for referring image segmentation
    Xiaoyan Jiang, Hang Yang, Kaiying Zhu, and 3 more authors
    In 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
    PDF Video Code
  12. PR
    Rethinking iterative stereo matching from a diffusion bridge model perspective
    Yuguang Shi, Sifan Zhou, Wei Wang, and 1 more author
    Pattern Recognition, 2025
    PDF
  13. ICML 2025
    RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
    Chen Xu, Yuxuan Yue, Zukang Xu, and 6 more authors
    In International Conference on Machine Learning, 2025
    PDF
  14. ICML 2025
    MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
    Zhixuan Chen, Xing Hu, Dawei Yang, and 5 more authors
    In International Conference on Machine Learning, 2025
    PDF
  15. ICLR 2025
    OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
    Xing Hu, Yuan Cheng, Dawei Yang, and 5 more authors
    In The Thirteenth International Conference on Learning Representations, 2025
    PDF Code
  16. ICLR 2025
    MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
    Zukang Xu, Yuxuan Yue, Xing Hu, and 6 more authors
    In The Thirteenth International Conference on Learning Representations, 2025
    PDF
  17. Arxiv
    Mano Technical Report
    Tianyu Fu, Anyang Su, Chenxu Zhao, and 8 more authors
    arXiv preprint arXiv:2509.17336, 2025
    PDF

2024

  1. Arxiv
    I-llm: Efficient integer-only inference for fully-quantized low-bit large language models
    Xing Hu, Yuan Cheng, Dawei Yang, and 4 more authors
    arXiv preprint arXiv:2405.17849, 2024
    PDF
  2. Arxiv
    Wkvquant: Quantizing weight and key/value cache for large language models gains more
    Yuxuan Yue, Zhihang Yuan, Haojie Duanmu, and 3 more authors
    arXiv preprint arXiv:2402.12065, 2024
    PDF
  3. ICLR 2024
    LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
    Sifan Zhou, Liang Li, Xinyu Zhang, and 6 more authors
    In International Conference on Learning Representations (ICLR), 2024
    PDF

2022

  1. TMM
    Real-time 3D single object tracking with transformer
    Jiayao Shan*, Sifan Zhou*, Yubo Cui, and 1 more author
    IEEE Transactions on Multimedia, 2022
    PDF Video Code

2021

  1. BMVC 2021
    3d object tracking with transformer
    Yubo Cui, Zheng Fang, Jiayao Shan, and 2 more authors
    32nd British Machine Vision Conference 2021, 2021
    PDF Code
  2. IROS 2021
    PTT: Point-track-transformer module for 3D single object tracking in point clouds
    Jiayao Shan*, Sifan Zhou*, Zheng Fang, and 1 more author
    In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
    PDF Video Code