Zhanpeng Luo

I'm a senior undergraduate student majoring in computer science at the University of Pittsburgh. I I am now interested in data-driven method for 3D perception and generation.

Things I would like to research on the next stage:

  • Generative 3D reconstructor that can hallucinate the unseen regions and generalize from object-level to scene-level.
  • Post-training for world model for better 3D consistency, camera controlbility and generalibility.

Email  /  CV  /  Scholar  /  Github  /  LinkedIn

profile photo

Publications
Instant4D: 4D Gaussian Splatting in Minutes
Zhanpeng Luo, Haoxi Ran Li Lu
NeurIPS 2025
project page / paper

With dense initialization form deep visual SLAM, we simplify the formulation and accelerate the optmization of 4D Gaussian Splatting.

pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
Zhanpeng Luo, Ce Zhang, Silong Yong, Cunxi Dai, Qianwei Wang, Haoxi Ran Guanya Shi, Katia P. Sycara Yaqi Xie
In submission, 2025
project page / paper

Teach MLLM Agent to use 3D visual tool, to reason in 3D space and to solve spatial reasoning problems.

UniPred: Unifying Deep Predicate Invention with Foundation Models
Qianwei Wang*, Bowen Li*, Zhanpeng Luo, Yifan Xu, Alexander Gray, Tom Silver, Sebastian Scherer, Katia Sycara Yaqi Xie
In submission, 2026
project page / paper

An LLM-in-the-loop agentic framework for discovering and optimizing neural symbolic predicates on real images.

Experience

  • Research Intern, supervised by Prof. Sycara, hosted by RISS program. June 2025 - Present
  • Research Intern, supervised by Bernhard Kerbl. Aug 2024 - Oct 2024.
  • Research Intern at West China Hospital. May 2023 - Sep 2023
  • Conference Reviewer: ICLR 2026
  • Award: Dean List: 6/6; NeurIPS Scholar Award

Something I want to share at the end

Steal this website's from Jon Barron. Like his talk at 3DV 2025.