Welcome to Yuheng Zha’s page!

I’m actively looking for internship opportunities in 2025 summer. Please feel free to reach out to me if you are interested in working with me.

Bio

I’m a PhD student in Halıcıoğlu Data Science Institute (HDSI) at UC San Diego, advised by Professor Zhiting Hu. I got my Bachelor’s degree (with Honors) from Zhejiang University.

Research Interests

My research interest lies in Natural Language Processing and Vision-Language models. Specificcally, I have explored ways to build an efficient but versatile model for many NLP tasks (Text Alignment) and a metric for evaluating factual consistency (AlignScore) of generative language models. I’m also interested in improving students’ accessibility in classes, where they can ask LMTutor their academic or logistic questions. The video (World Model) is the latest one towards vision-language understanding and video generation. Curently, I’m actively doing research in

• Natural Language Processing
  • Natural Language Understanding: Evaluation of NLG models, especially the factual consistency of the generative language models
  • Natural Language Generation: Generating factual text given context or knowledge
• Multi-modal Learning: Vision and Language
  • Visual Concept Learning: Incrementally and sequentially learning concepts from visual inputs (e.g., images, videos)