Image
Yitian Zhang
PhD Student
Electrical and Computer Engineering Department
Northeastern University
Email : markcheung9248 [at] gmail.com    

About Me

I am a fifth-year PhD student in the Electrical and Computer Engineering Department, Northeastern University, advised by Prof. Yun Raymond Fu. Prior to this, I obtained my bachelor degree from Huazhong University of Science and Technology. My research interests center around Efficient and Scalable AI, spanning Generative Models, Multimodal Large Language Models, and Foundation Models.

I am currently exploring full-time opportunities in industry and would welcome the chance to connect if there is an aligned interest.

News

  • 2026.02: We open-source Fine-T2I, a high-quality, high-resolution dataset designed to close the gap between open-source and enterprise-grade text-to-image models.
  • 2026.01: We have three papers accepted by ICLR 2026.
  • 2025.07: We have one paper accepted by NeurIPS 2025.
  • 2025.07: We have three papers accepted by ICCV 2025.
  • 2025.01: We have two papers accepted by ICLR 2025.
  • 2024.09: We have one paper accepted by NeurIPS 2024.
  • 2024.01: We have one paper accepted by ICLR 2024.
  • 2023.02: We have one paper accepted by CVPR 2023. We provide a codebase which supports 2D, 3D and Transformer Network for Video Recognition.
  • 2022.10: I have received NeurIPS 2022 scholar award.
  • 2022.09: We have two papers accepted by NeurIPS 2022.
  • 2021.09: Begin my journey at SMILE Lab, Northeastern University.

Experiences

    SMILE Lab, Northeastern University, Boston

    Graduate Student,   Sep. 2021 ~ Now

    Supervisor: Prof. Yun Raymond Fu

Image

    Adobe Research, San Jose

    Research Intern,   June. 2024 ~ Now

    Supervisor: Long Mai, Aniruddha Mahapatra

Image

    Snap Inc., New York

    Research Intern,   May. 2023 ~ Aug. 2023

Image

    Hong Kong University of Science and Technology, Hong Kong

    Research Assistant,   Apr. 2021 ~ Jul. 2021

    Supervisor: Prof. Qifeng Chen

Image

    Tsinghua University, Beijing

    Research Assistant,   Jul. 2020 ~ Dec. 2020

    Supervisor: Prof. Gao Huang

Image

    National Tsing Hua University, Taiwan

    Exchange Student,   Sep. 2019 ~ Jan. 2020

Image

    National University of Singapore, Singapore

    Research Assistant,   Jul. 2019 ~ Sep. 2019

    Supervisor: Prof. Marcelo Ang

Image

    Huazhong University of Science and Technology, Wuhan

    Undergraduate Student,   Sep. 2016 ~ Jun. 2020

Image

Publications

Image
Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning
Xu Ma, Yitian Zhang, Qihua Dong, Yun Fu
[Dataset Explorer] [Dataset] [arXiv]
Image
Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
Qihua Dong, Kuo Yang, Lin Ju, Handong Zhao, Yitian Zhang, Yizhou Wang, Huimin Zeng, Jianglin Lu, Yun Fu
International Conference on Learning Representations (ICLR), 2026.
[arXiv]
Image
SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
Yiyang Huang, Liang Shi, Yitian Zhang, Yi Xu, Yun Fu
International Conference on Learning Representations (ICLR), 2026.
[arXiv]
Image
GmNet: Revisiting Gating Mechanisms From A Frequency View
Yifan Wang, Xu Ma, Yitian Zhang, Yizhou Wang, Zhongruo Wang, Sung-Cheol Kim, Vahid Mirjalili, Vidya Renganathan, Yun Fu
International Conference on Learning Representations (ICLR), 2026.
[arXiv]
Image
The Indra Representation Hypothesis
Jianglin Lu, Hailing Wang, Kuo Yang, Yitian Zhang, Simon Jenni, Yun Fu
Advances in Neural Information Processing Systems (NeurIPS), 2025.
[arXiv]
Image
Outlier-Aware Post-Training Quantization for Image Super-Resolution
Hailing Wang, Jianglin Lu, Yitian Zhang, Yun Fu
International Conference on Computer Vision (ICCV Highlight), 2025.
[arXiv]
Image
REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder
Yitian Zhang, Long Mai, Aniruddha Mahapatra, David Bourgin, Yicong Hong, Jonah Casebeer, Feng Liu, Yun Fu
International Conference on Computer Vision (ICCV), 2025.
[arXiv] [Website]
Image
Progressive Growing of Video Tokenizers for Highly Compressed Latent Spaces
Aniruddha Mahapatra, Long Mai, Yitian Zhang, David Bourgin, Feng Liu
International Conference on Computer Vision (ICCV), 2025.
[arXiv] [Website]
Image
Accessing Vision Foundation Models via ImageNet-1K
Yitian Zhang, Xu Ma, Yue Bai, Huan Wang, Yun Fu
International Conference on Learning Representations (ICLR), 2025.
[arXiv] [Code] [知乎]
Image
Scale-Free Graph-Language Models
Jianglin Lu, Yixuan Liu, Yitian Zhang, Yun Fu
International Conference on Learning Representations (ICLR), 2025.
[arXiv] [Code]
Image
Slicing Vision Transformer for Flexible Inference
Yitian Zhang, Huseyin Coskun, Xu Ma, Huan Wang, Ke Ma, Xi Chen, Derek Hao Hu, Yun Fu
Advances in Neural Information Processing Systems (NeurIPS), 2024.
[arXiv] [Code]
Image
Don't Judge by the Look: A Motion Coherent Augmentation for Video Recognition
Yitian Zhang, Yue Bai, Huan Wang, Yizhou Wang, Yun Fu
International Conference on Learning Representations (ICLR), 2024.
[arXiv] [Code]
Image
Frame Flexible Network
Yitian Zhang, Yue Bai, Chang Liu, Huan Wang, Sheng Li, Yun Fu
IEEE / CVF Computer Vision and Pattern Recognition (CVPR), 2023.
[arXiv] [Code] [知乎]
Image
Look More but Care Less in Video Recognition
Yitian Zhang, Yue Bai, Huan Wang, Yi Xu, Yun Fu
Advances in Neural Information Processing Systems (NeurIPS), 2022.
[arXiv] [Code]
Image
Parameter-Efficient Masking Network
Yue Bai, Huan Wang, Xu Ma, Yitian Zhang, Zhiqiang Tao, Yun Fu
Advances in Neural Information Processing Systems (NeurIPS), 2022.
[arXiv] [Code]
Image
Spatially Adaptive Feature Refinement for Efficient Inference
Yizeng Han, Gao Huang, Shiji Song, Le Yang, Yitian Zhang, Haojun Jiang
IEEE Transactions on Image Processing (TIP), 2021.
[Paper]

Professional Activities

  • Reviewer for CVPR, NeurIPS, ICLR, ICML, ICCV, ECCV, TPAMI, TIP, TKDD