GRASP Lab, University of Pennsylvania

Sep 1, 2025 · 1 min read
internships

Overview

Graduate Researcher University of Pennsylvania, 2025 – 2026

World Models for Robotic Manipulation

  • Conducted research on 3D scene reconstruction, temporal representation learning, and world models for embodied decision-making systems.
  • Explored unified frameworks connecting perception, dynamic scene understanding, and planning for robotic manipulation tasks.
  • Focused on learning environment representations that support downstream control and long-horizon reasoning.

Training and Evaluation Infrastructure

  • Responsible for model training, experimental debugging, and large-scale dataset preprocessing.
  • Optimized training workflows and experiment pipelines to improve reproducibility and computational efficiency.
  • Participated in simulation environment design and benchmark evaluation for manipulation tasks.

Research Analysis

  • Surveyed and analyzed recent literature in embodied AI, generative world models, and robotic learning.
  • Developed experimental comparison frameworks and performance evaluation protocols for research studies.
Robotics World Models 3D Vision Embodied AI Manipulation
YiFan Cai
Authors
YiFan Cai (he/him)
Graduate student
I am a graduate student in Systems Engineering at the University of Pennsylvania, with a B.S. in Computer Science from ShanghaiTech University. I have research experience in diffusion models, computer vision, robotic manipulation, and molecular drug design. My current interests focus on world models, computer vision, and artificial intelligence.