Joanna(Jiahuan) Cheng

I am a combined B.S./M.S.E. student in Computer Science at Johns Hopkins University, where I work with Prof. Homanga Bharadhwaj and Prof. Anand Bhattad. I am also currently a Research Intern at the Harvard Kempner Institute, working with Prof. Qianqian Wang and Prof. Yilun Du.

I am interested in how machines can understand the dynamics of the physical world — how scenes are structured, how things move, and how they interact. I am especially interested in how this understanding can support robots that perceive, predict, and act in the real world.

I am applying to PhD programs for Fall 2027, and looking for research internship positions starting Spring 2027.

• Google Scholar
• Email
• X
• GitHub

News

• Sep 2026MoSE3 was accepted to NeurIPS 2026 as a Spotlight!
• Jul 2026Started as a Research Intern at the Harvard Kempner Institute with Qianqian Wang.

Selected Publications

• MoSE3: Learning World-Space SE(3) at Every Pixel

  Jiahuan Cheng*, Zhiyi Li*, Tian Xia*, Ruojin Cai, Yilun Du, Qianqian Wang

  NeurIPS, 2026 Spotlight

  arXivCodeProject
• 
  SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

  Mengjiao Ma*, Qi Ma*, Yue Li*, Jiahuan Cheng, Runyi Yang, Bin Ren, Nikola Popovic, Mingqiang Wei, Nicu Sebe, Luc Van Gool, Theo Gevers, Martin R. Oswald, Danda Pani Paudel

  NeurIPS Datasets and Benchmarks Track, 2025

  arXivCodeProject
• Occam's LGS: An Efficient Approach for Language Gaussian Splatting

  Jiahuan Cheng, Jan-Nico Zaech, Luc Van Gool, Danda Pani Paudel

  BMVC, 2025

  arXivCodeProject

All publications →

Education