avatar

Shu Zhao

Machine Learning Engineer
NVIDIA
shuzhao.cs@gmail.com


About Me

I am a Senior Machine Learning Engineer at NVIDIA. I completed my Ph.D. at Pennsylvania State University, advised by Prof. Vijaykrishnan Narayanan.

Research Interests

News

more...
  • [Dec. 2025] Successfully defended my Ph.D. dissertation!
  • [Oct. 2025] We have released ferret, an extensible RL framework for training LLM agents with advanced search capabilities.
  • [Jun. 2025] Our paper, "HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?" was accepted at ICCV 25.
  • [May 2025] One paper was accepted at ICML 2025.
  • [Mar. 2025] I will be interning at NVIDIA this summer. See you in Santa Clara!

Selected Works

  1. arXiv
    Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation
    Shu Zhao, Tan Yu
    arXiv:2610.28586. 2026.
    PDF Code

  2. NeurIPS
    The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors
    Shu Zhao, Tan Yu
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2026 Spotlight
    PDF Code

  3. ICLR
    MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition
    Shu Zhao, Nilesh Ahuja, Tan Yu, Tianyi Shen, Vijaykrishnan Narayanan
    International Conference on Learning Representations (ICLR), 2026
    PDF Code

  4. arXiv
    ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
    Shu Zhao, Tan Yu, Anbang Xu, Japinder Singh, Aaditya Shukla, Rama Akkiraju
    arXiv:2508.09303. 2025.
    PDF Code

  5. AAAI
    KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing
    Shu Zhao, Tan Yu, Xiaoshuai Hao, Wenchao Ma, Vijaykrishnan Narayanan
    AAAI Conference on Artificial Intelligence (AAAI), 2025
    PDF Code

  6. CVPR
    Learning Conditional Space-Time Prompt Distributions for Video Class-Incremental Learning
    Xiaohan Zou, Wenchao Ma, Shu Zhao
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Highlight
    PDF

  7. ICML
    SafeMap: Robust HD Map Construction from Incomplete Observations
    Xiaoshuai Hao, Lingdong Kong, Rong Yin, Pengwei Wang, Jing Zhang, Yunfeng Diao, Shu Zhao
    International Conference on Machine Learning (ICML), 2025
    PDF

  8. IJCAI
    Rescuing Deep Hashing from Dead Bits Problem
    Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang
    International Joint Conference on Artificial Intelligence (IJCAI), 2021.
    PDF

  9. ACM MM
    Asymmetric Deep Hashing for Efficient Hash Code Compression
    Shu Zhao, Dayan Wu, Wanqian Zhang, Yu Zhou, Bo Li, Weiping Wang
    ACM International Conference on Multimedia (ACM MM), 2020 Oral
    PDF

Services

Conference Reviewers

Teaching Assistant


Powered by Jekyll and Minimal Light theme. Last Updated: Oct 20, 2026.