Zihan (Nick) Su 苏梓涵

S.M. student in Data Science at Harvard. I work on multimodal foundation models, video world models, and structured generative modeling.

Open to Summer 2027 research / ML internships

Portrait of Zihan Su

I study how structured representations can make multimodal and generative models more capable, from non-Euclidean geometry to action-conditioned video generation.

Recent work covers Flow Matching, hierarchical tokenization, pretrained VLM adaptation, and world models for robot planning.

  • Multimodal Foundation Models
  • Video World Models
  • Geometric Deep Learning
  • Structured Representations
  • Spatial / Embodied AI
  1. NeurIPS 2026First author

    Umbilic Multinomial Logistic Regression

    Zihan Su, Nicu Sebe, Bernhard Schölkopf, Ziheng Chen

    Extends multinomial logistic regression to umbilic Riemannian geometries, giving one classifier for non-Euclidean representation learning.

  2. ICLR 2026Co-first author

    Proper Velocity Neural Networks

    Ziheng Chen*, Zihan Su*, Bernhard Schölkopf, Nicu Sebe  ·  *equal contribution

    A full neural-network framework for the unconstrained Proper Velocity model. Best MCC on all five TEB benchmarks, with an 8.3-point gain over HCNN-S on SINEs.

DeerMe.AI — Camera-Based AI Physical Coaching

Co-founded and led the technical side of a mobile coaching app that reads human keypoints to give real-time form feedback. React Native client, Python vision services, 39 automated tests.