Zhilin(Hadlay) Zhang

photo.jpeg

Hi! I’m a Master student in Computer Science at NYU Tandon. Previously, I obtained my Bachelor of Engineering degree in Computer Science from Tongji University. Currently, I’m working as a Research Intern at Stony Brook University, advised by Prof. Chenyu You.

My research interests focus on developing more capable and reliable AI systems through two main directions:

a) Multi-modal AI, especially in the context of human-like perception and reasoning ability in different modalities (vision, language, audio and so on), and its application in the domains like (Medical) Visual Question Answering, and Image Captioning.

b) LLM-based Agents, specifically multi-agent systems with dynamic communication protocols and task decomposition mechanisms that can collaborate and coordinate to solve complex real-world problems.

I am actively looking for a 2026 Fall PhD position. Please contact me if you have relevant opportunities!

news

Aug 26, 2025 Our paper “PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs” has been released :tada: arXiv Code
May 01, 2025 Started as Summer Research Intern at Stony Brook University :tada:
Mar 31, 2025 Two papers were accepted by IJCNN 2025 :tada:
Jan 21, 2025 Started my role as Teaching Assistant for CS-GY 6233: Intro to OS :rocket:
Oct 30, 2024 Our paper “Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approach” is accepted by CVCI 2025 :tada:
Sep 03, 2024 I started my MS in Computer Science at NYU Tandon. :star2:
Jul 01, 2024 I received my B.E. degree in Computer Science from Tongji University.
Jun 28, 2024 Our patent is published. :tada: Link
Jan 19, 2024 Last day of my internship at Momenta. :raised_hands:
Sep 30, 2023 Last day of my internship at Ronovo Surgical. :raised_hands:

selected publications

  1. postergen.png
    PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
    Zhilin Zhang, Xiang Zhang, Jiaqi Wei, and 2 more authors
    2025
    PDF
  2. Framework.drawio.png
    SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment
    Jie Wang, Yichen Wang, Zhilin Zhang, and 3 more authors
    Under Review, 2024
    PDF
    0 Google Scholar citations
  3. IJCNN 2025
    model.png
    Efficient Bilinear Attention-based Fusion for Medical Visual Question Answering
    Zhilin Zhang, Jie Wang, Zhanghao Qin, and 2 more authors
    Accepted by IJCNN 2025, 2024
    PDF
    0 Google Scholar citations