Fan-Yun Sun
Scholar

Fan-Yun Sun

Google Scholar ID: TOw2RMMAAAAJ
Ph.D. candidate at Computer Science, Stanford University
Embodied AICode GenerationComputer Graphics/VisionGraph Machine Learning
Citations & Impact
All-time
Citations
1,932
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
16
list available
Resume (English only)
Academic Achievements
  • - Publications: 'ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code' (NeurIPS 2025)
  • - '3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds' (To appear)
  • - 'Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images' (ACL 2025)
  • - 'LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models' (CVPR 2025)
  • - 'GRS: Generating Robotic Simulation Tasks from Real-World Images' (CVPR Workshop 2025)
  • - 'Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition' (EMNLP 2024)
  • - 'FactorSim: Generative Simulation via Factorized Representation' (NeurIPS 2024)
  • - 'Holodeck: Language-Guided Generation of 3D Embodied Environments' (CVPR 2024)
  • - 'Partial-View Object View Synthesis via Filtering Inversion' (Workshop XRNeRF, CVPR 2023; 3DV 2024)
  • - 'Interaction Modeling with Multiplex Attention'
  • - Awards: The Google Graduate Fellowship in Computer Science
Research Experience
  • - Work Experience: Extensive work with NVIDIA Research, including the Learning and Perception Research Group, Metropolis Deep Learning (Omniverse), and the Autonomous Vehicle Research Group
  • - Research Projects: Holodeck, FactorSim, GRS, LayoutVLM, etc.
  • - Position: PhD Candidate
Education
  • - Degree: Master's and PhD in Computer Science
  • - School: Stanford University
  • - Advisors: Nick Haber, Jiajun Wu, etc.
  • - Time: Currently in the final year of the PhD program
  • - Major: Computer Science
Background
  • - Research Interests: generating embodied (3D) environments and data to train robotics/RL policies, particularly towards advancing embodied, multi-modal foundational models and their reasoning abilities
  • - Professional Field: Artificial Intelligence, Machine Learning, Computer Vision
  • - Brief Introduction: A final-year CS PhD Candidate at Stanford University, affiliated with the Stanford AI Lab, Autonomous Agents Lab, and Stanford Vision and Learning Lab.
Miscellany
  • - Personal Interests: Occasionally writes on X, builds AI applications to experiment with new ways of creating, enjoys hosting conferences/bootcamps
  • - Social Media: LinkedIn, Twitter, GitHub, Scholar