Hello, I'm Jiezhi "Stephen" Yang

I am a second year Master’s student in Computational Science Engineering at Harvard University, cross-registered at MIT. I received my B.A. in Computer Science and Cognitive Science from UC Berkeley, where I graduated from the EECS Honors Program with high distinction.

I am interested in building vision-conditioned agents that learn and reason in 3D. At Berkeley, I was fortunate to work at RISE and BAIR Lab under Prof. Joseph Gonzalez and Trevor Darrell, with Ph.D. candidate Charles Packer, Lisa Dunlap, and Alvin Wan. I also appreciate my experience beiefly collaborating with Harvard CVG, Interactive Robotics Group and MIT CSAIL.

I am on the job market for 2025 New Grad opportunities. Please contact me at stephenyang@berkeley.edu!


News

  • July 2024: I have my first-authored paper CARFF accepted at ECCV 2024.
  • May 2024: I am joining Qualcomm for a MLE summer internship.
  • August 2023: I joined Harvard CSE, and got a paper accepted at NeurIPS 2023.
  • May 2023: I have graduated from UC Berkeley with high distinction.

Publications

CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting

CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting

ECCV 2024

We predict future 3D scenes given past 2D observations, such as 2D ego-centric image in autonomous driving settings.

Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation

Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation

NeurIPS 2023

We used natural language descriptions with vision models to generate useful variations of the training data for data augmentation.

DreamScenes: 3D Textured Scene Generation Via Compositional Diffusions

DreamScenes: 3D Textured Scene Generation Via Compositional Diffusions

Draft Paper

Text-conditioned 3D generation via multistep diffusion, LLM, ControlNet, and differentiable rendering.


Industry

Machine Learning Engineer Intern, Qualcomm Inc.

Machine Learning Engineer Intern, Qualcomm Inc.

May - August 2024

Spearheaded the pivotal deep learning efforts in new sensor research with the multi-media group.

Software Engineer Intern, Robert Bosch (Research Department)

Software Engineer Intern, Robert Bosch (Research Department)

May - August 2021

Researched on modeling Radar, LIDAR, and camera data for infrastructure based autonomous driving.


Miscellaneous

I was born in the beautiful, German-style coastal city of Tsingtao. I like VR games and photography, espacially aerial photography with drones. I am also trying to improve my very much out of practice piano skills…