CV

Summary

I am a Ph.D. candidate in Computer Engineering at Northeastern University. I study how multimodal agents use tools and learn from feedback, how vision-language models understand long videos, and why they hallucinate.

Education

  • Ph.D. in Computer Engineering
    Sep 2024 – May 2029 (expected)
    Northeastern University, Boston, MA
    Advised by Prof. Yun Raymond Fu.
  • M.S. in Computer Science
    Sep 2021 – Jun 2024
    Xidian University, Xi’an, China
    Advised by Prof. Xuefeng Liang.
  • B.Eng. in Intelligence Science and Technology
    Sep 2017 – Jun 2021
    Xidian University, Xi’an, China

Research and Industry Experience

  • Ph.D. Candidate
    Sep 2024 – Present
    Northeastern University, Boston, MA
    Advised by Prof. Yun Raymond Fu.
    • Developed RACER, a training-free agent that decomposes questions, retrieves video frames, and refines its search using visual feedback. Across four video LLMs, it improved accuracy over uniform sampling by 4.3–6.6 percentage points on Video-MME, MLVU, and LongVideoBench.
    • Developed SHIELD to address encoder bias with inference-time token interventions and adversarial contrastive decoding. It reduced captioning hallucinations by 27% relative to the baseline across multiple vision-language model families.
    • Developed D-CoDe to adapt image-pretrained models to video question answering through question decomposition and dynamic frame and token compression. It improved accuracy on egocentric videos by 29% relative to the LLaVA-NeXT-7B baseline.
  • Research Intern
    May 2026 – Nov 2026
    Adobe Research, San Jose, CA
    Studied multimodal agents, VLM reasoning, and self-improvement with mentors Zhaowen Wang and Shraman Pramanick.
    • Built DesignJudge, a dataset of 7,475 layout preference pairs. Post-trained Qwen3.5-9B and Qwen3.8-27B to critique and score layouts.
    • Developed a loop in which a VLM evaluator critiques a layout, a Codex agent edits it, and the evaluator scores the result. Used the resulting preference pairs for iterative GRPO training.
    • GRACE-27B reached 83.7% accuracy on DesignJudge. In a user study, a majority of raters preferred GRACE-guided edits to Gemini-guided edits on 70% of the Crello layouts.
  • Research Intern
    May 2025 – Nov 2025
    Adobe Research, San Jose, CA
    Mentored by Zhaowen Wang, Simon Jenni, and Jing Shi.
    • Developed MASON to ground layout metadata in the image and model the 3D structure of design elements. With Qwen2.5-VL-7B as its backbone, MASON achieved relative improvements of 26% over Gemini-2.5-Pro and 15% over GPT-5/GPT-o3.
    • Built CoDeLayout, a benchmark of approximately 20,000 examples, by mining compositional structure and generating multimodal questions and answers.

Skills

Languages

  • Python
  • LaTeX

Machine learning

  • PyTorch
  • Hugging Face Transformers
  • Hugging Face Datasets

Training and fine-tuning

  • Accelerate
  • PEFT
  • bitsandbytes

Reinforcement learning and post-training

  • TRL
  • verl
  • OpenRLHF

Inference and evaluation

  • vLLM
  • lmms-eval

Video processing

  • FFmpeg
  • PyAV
  • decord

Systems and infrastructure

  • Linux
  • Git
  • Slurm

Publications

First-Author Papers

  • SHIELD: Suppressing Hallucinations in LVLM Encoders via Bias and Vulnerability Defense
    2026
    Yiyang Huang, Liang Shi, Yitian Zhang, Yi Xu, Yun Fu
    ICLR
  • Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models
    2026
    Yiyang Huang, Zhaowen Wang, Simon Jenni, Jing Shi, Yitian Zhang, Yizhou Wang, Yun Fu
    ECCV
  • Distorted or Fabricated? A Survey on Hallucination in Video LLMs
    2026
    Yiyang Huang, Yitian Zhang, Yizhou Wang, Mingyuan Zhang, Liang Shi, Huimin Zeng, Yun Fu
    ACL
  • D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
    2025
    Yiyang Huang, Yizhou Wang, Yun Fu
    EMNLP
  • CALLip: Lipreading using Contrastive and Attribute Learning
    2021
    Yiyang Huang, Xuefeng Liang, Chaowei Fang
    ACM MM
  • When Plausibility Fails: Learning Human-Aligned Layout Evaluation with VLMs
    Yiyang Huang, Zhaowen Wang, Shraman Pramanick, Yun Fu
    Under review
  • RACER: Reflective Agent Coupling Query Interpretation and Tool-Based Retrieval for Frame Selection in Long Video Understanding
    2026
    Yiyang Huang, Yitian Zhang, Yizhou Wang, Jianglin Lu, Qihua Dong, Hailing Wang, Huimin Zeng, Mingyuan Zhang, Yun Fu
    Preprint

Selected Co-Authored Papers

  • StreamVLM: Adapting Offline Vision-Language Models for Streaming Understanding
    Hailing Wang, Jianglin Lu, Xu Ma, Yiyang Huang, Yun Fu
    Under review
  • Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models
    2025
    Mingyuan Zhang, Yue Bai, Yifan Wang, Yiyang Huang, Yun Fu
    Preprint
  • Capturing Individual Differences of Facial Expression for Authentic Expression Generation
    2026
    Liang Shi, Yiyang Huang, Yun Fu
    IEEE FG

Academic Service

  • Conference reviewer · ICLR, NeurIPS, ACL, EMNLP, WWW, IEEE Face & Gesture (FG)
  • Journal reviewer · ACM TKDD

Awards

  • 2022 · Outstanding Student, Xidian University
  • 2021 · National Scholarship, China
  • 2021 · First Prize, Undergraduate Computer Design Competition (National Level), China
  • 2019 · Second Prize, RoboMaster National Robotics Competition, China
  • 2019 · Third Prize, ICRA AI Challenge