publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. agent0.png
    Agent0: Unleashing self-evolving agents from zero data via tool-integrated reasoning
    Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, and Huaxiu Yao
    arXiv preprint arXiv:2511.16043, 2025
    AgentSelf-evolving
    arXiv Code GitHub stars
  2. unidoc-bench.png
    UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG
    Xiangyu Peng*, Can Qin*, Zeyuan Chen, Ran Xu, Caiming Xiong, and Chien-Sheng Wu
    arXiv preprint arXiv:2510.03663, 2025
    *Equal Contribution
    Doc UnderstandingMultimodal
    arXiv Code GitHub stars
  3. coda.gif
    CoDA: Coding LM via Diffusion Adaptation
    Haolin Chen*, Shiyu Wang*, Can Qin*, Bo Pang, Zuxin Liu, Jielin Qiu, Jianguo Zhang, Yingbo Zhou, Zeyuan Chen, Ran Xu, and  others
    arXiv preprint arXiv:2510.03270, 2025
    *Core Contribution
    Code GenerationDiffusion LLM
    arXiv Code GitHub stars
  4. mmeb-v2.png
    Vlm2vec-v2 (MMEB-V2): Advancing multimodal embedding for videos, images, and visual documents
    Rui Meng, Ziyan Jiang, Ye Liu, Mingyi Su, Xinyi Yang, Yuepeng Fu, Can Qin, Zeyuan Chen, Ran Xu, Caiming Xiong, and  others
    Transactions on Machine Learning Research (TMLR), 2025
    Embedding ModelMultimodal
    arXiv Code GitHub stars Website
  5. holitom.png
    HoliTom: Holistic Token Merging for Fast Video Large Language Models
    Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    Video LLMToken Compression
    arXiv Code GitHub stars
  6. token-compression-survey.png
    When Tokens Talk Too Much: A Survey of Multimodal Long-context Token Compression across Images, Videos, and Audios
    Kele Shao, Keda Tao, Kejia Zhang, Sicheng Feng, Mu Cai, Yuzhang Shang, Haoxuan You, Can Qin, Yang Sui, and Huan Wang
    Transactions on Machine Learning Research (TMLR), 2025
    Token CompressionSurveyMultimodal
    arXiv Code GitHub stars
  7. image-blip3o.jpg
    BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
    Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou, Saining Xie, Silvio Savarese, and  others
    arXiv preprint arXiv:2505.09568, 2025
    Unified Multimodal Model
    arXiv Code GitHub stars
  8. vidkv.png
    Plug-and-Play 1. x-Bit KV Cache Quantization for Video Large Language Models
    Keda Tao, Haoxuan You, Yang Sui, Can Qin, and Huan Wang
    arXiv preprint arXiv:2503.16257, 2025
    Video LLMToken Compression
    arXiv Code GitHub stars
  9. cogalign.png
    Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding
    Kung-Hsiang Huang, Can Qin, Haoyi Qiu, Philippe Laban, Shafiq Joty, Caiming Xiong, and Chien-Sheng Wu
    Annual Meeting of the Association for Computational Linguistics (Findings), 2025
    VLMChartGeometry
    arXiv Code GitHub stars
  10. dycoke-demo.gif
    DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
    Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    Video LLMToken Compression
    arXiv Code GitHub stars

2024

  1. xgen-mm-vid1.gif
    xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs
    Michael S Ryoo, Honglu Zhou, Shrikant Kendre, Can Qin, Le Xue, Manli Shu, Silvio Savarese, Ran Xu, Caiming Xiong, and Juan Carlos Niebles
    arXiv preprint arXiv:2410.16267, 2024
    Video LLMToken Compression
    arXiv Website
  2. xgen-videosyn-1.gif
    xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
    Can Qin, Congying Xia, Krithika Ramakrishnan, Michael Ryoo, Lifu Tu, Yihao Feng, Manli Shu, Honglu Zhou, Anas Awadalla, Jun Wang, and  others
    arXiv preprint arXiv:2408.12590, 2024
    DiffusionVideo Generation
    arXiv
  3. blip3.png
    xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
    Le Xue, Manli Shu, Anas Awadalla, Jun Wang, An Yan, Senthil Purushwalkam, Honglu Zhou, Viraj Prabhu, Yutong Dai, Michael S Ryoo, and  others
    arXiv preprint arXiv:2408.08872, 2024
    VLMMultimodal
    arXiv Code GitHub stars
  4. preference_data_st_llava_med.png
    Self-Training Large Language and Vision Assistant for Medical
    Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang, and Zhiqiang Tao
    In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
    VLMMedical
    arXiv Code GitHub stars
  5. sq-llava.png
    SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
    Guohao Sun, Can Qin, Jiamian Wang, Zeyuan Chen, Ran Xu, and Zhiqiang Tao
    European Conference on Computer Vision (ECCV), 2024
    VLMMultimodal
    arXiv Code GitHub stars
  6. hive.png
    HIVE: Harnessing Human Feedback for Instructional Visual Editing
    Shu Zhang*, Xinyi Yang*, Yihao Feng*, Can Qin, Chia-Chih Chen, Ning Yu, Zeyuan Chen, Huan Wang, Silvio Savarese, Stefano Ermon, Caiming Xiong, and Ran Xu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    DiffusionImage EditingHuman-in-the-loop
    arXiv Code GitHub stars

2023

  1. arXiv
    Why is the state of neural network pruning so confusing? on the fairness, comparison setup, and trainability in network pruning
    Huan Wang, Can Qin, Yue Bai, and Yun Fu
    arXiv:2301.05219, 2023
    arXiv Code GitHub stars
  2. unicontrol.png
    UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
    Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, Stefano Ermon, Yun Fu, and Ran Xu
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    DiffusionControllable Image Generation
    arXiv Code GitHub stars Website
  3. gluegen.png
    GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
    Can Qin, Ning Yu, Chen Xing, Shu Zhang, Zeyuan Chen, Stefano Ermon, Yun Fu, Caiming Xiong, and Ran Xu
    International Conference on Computer Vision (ICCV), 2023
    DiffusionMultimodalImageTextAudio
    arXiv Code GitHub stars Website
  4. TIP
    Balancing biases and preserving privacy on balanced faces in the wild
    Joseph P Robinson, Can Qin, Yann Henon, Samson Timoner, and Yun Fu
    IEEE Transactions on Image Processing, 2023
    arXiv Code GitHub stars
  5. TPAMI
    Global Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
    Huan Wang, Yulun Zhang, Can Qin, Luc Van Gool, and Yun Fu
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
    PDF Code
  6. CVPR
    Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
    Vibashan VS, Ning Yu, Chen Xing, Can Qin, Mingfei Gao, Juan Carlos Niebles, Vishal M Patel, and Ran Xu
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    PDF Code GitHub stars
  7. ICLR Oral
    Image as Set of Points
    Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, and Yun Fu
    In The Eleventh International Conference on Learning Representations (ICLR), 2023
    arXiv Code GitHub stars

2022

  1. arXiv
    A Close Look at Spatial Modeling: From Attention to Convolution
    Xu Ma, Huan Wang, Can Qin, Kunpeng Li, Xingchen Zhao, Jie Fu, and Yun Fu
    arXiv preprint arXiv:2212.12552, 2022
    arXiv Code GitHub stars
  2. ICDM
    Making Reconstruction-based Method Great Again for Video Anomaly Detection
    Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, and Yun Fu
    In 2022 IEEE International Conference on Data Mining (ICDM), 2022
    arXiv Code GitHub stars
  3. TIP
    Semi-Supervised Domain Adaptive Structure Learning
    Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, and Yun Fu
    IEEE Transactions on Image Processing, 2022
    arXiv
  4. KDD
    External Knowledge Infusion for Tabular Pre-training Models with Dual-adapters
    Can Qin, Sungchul Kim, Handong Zhao, Tong Yu, Ryan A Rossi, and Yun Fu
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
    PDF Code
  5. ICLR
    Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
    Xu Ma, Can Qin, Haoxuan You, Haoxi Ran, and Yun Fu
    In International Conference on Learning Representations (ICLR), 2022
    PDF Code GitHub stars
  6. ICLR
    Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning
    Yulun Zhang*, Huan Wang*, Can Qin, and Yun Fu
    In International Conference on Learning Representations (ICLR), 2022
    PDF Code GitHub stars
  7. Nature Comm
    Self-directed online machine learning for topology optimization
    Changyu Deng, Yizhou Wang, Can Qin, Yun Fu, and Wei Lu
    Nature communications, 2022
    PDF Code GitHub stars

2021

  1. FG
    The 5th recognizing families in the wild data challenge: Predicting kinship from faces
    Joseph P Robinson, Can Qin, Ming Shao, Matthew A Turk, Rama Chellappa, and Yun Fu
    In IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2021
    arXiv
  2. NeurIPS
    Slow learning and fast inference: Efficient graph similarity computation via knowledge distillation
    Can Qin, Handong Zhao, Lichen Wang, Huan Wang, Yulun Zhang, and Yun Fu
    Advances in Neural Information Processing Systems (NeurIPS), 2021
    PDF Code GitHub stars
  3. NeurIPS Spotlight
    Aligned structured sparsity learning for efficient image super-resolution
    Yulun Zhang*, Huan Wang*, Can Qin, and Yun Fu
    Advances in Neural Information Processing Systems (NeurIPS), 2021
    PDF Code GitHub stars
  4. ICCV
    Context reasoning attention network for image super-resolution
    Yulun Zhang, Donglai Wei, Can Qin, Huan Wang, Hanspeter Pfister, and Yun Fu
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021
    PDF
  5. ICLR
    Neural pruning via growing regularization
    Huan Wang, Can Qin, Yulun Zhang, and Yun Fu
    International Conference on Learning Representations (ICLR), 2021
    arXiv Code GitHub stars

2020

  1. CVPRW
    Face recognition: too bias, or not too bias?
    Joseph P Robinson, Gennady Livitz, Yann Henon, Can Qin, Yun Fu, and Samson Timoner
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020
    PDF Code GitHub stars
  2. ECCV
    Generative view-correlation adaptation for semi-supervised multi-view learning
    Yunyu Liu, Lichen Wang, Yue Bai, Can Qin, Zhengming Ding, and Yun Fu
    In European Conference on Computer Vision (ECCV), 2020
    PDF
  3. AAAI
    Dual relation semi-supervised multi-label learning
    Lichen Wang, Yunyu Liu, Can Qin, Gan Sun, and Yun Fu
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020
    PDF
  4. Remote Sensing
    Semi-supervised hyperspectral image classification via spatial-regulated self-training
    Yue Wu, Guifeng Mu, Can Qin, Qiguang Miao, Wenping Ma, and Xiangrong Zhang
    Remote Sensing, 2020
    PDF

2019

  1. NeurIPS
    Pointdan: A multi-scale 3d domain adaption network for point cloud representation
    Can Qin*, Haoxuan You*, Lichen Wang, C-C Jay Kuo, and Yun Fu
    Advances in Neural Information Processing Systems (NeurIPS), 2019
    PDF Code GitHub stars