I recently completed my Ph.D. at UC Berkeley in the Mechanical Systems Control Lab, affiliated with BAIR and Berkeley DeepDrive, advised by Prof. Masayoshi Tomizuka and Dr. Wei Zhan. I am supported by the NSF Graduate Research Fellowship Program and the Taiwan–UC Berkeley Fellowship.

My research focuses on developing safe and intelligent autonomous systems for complex, human-centered environments. Central to this work are machine learning, generative models, and reinforcement learning with applications in autonomous driving and robotics. A key aspect is to tackle challenges involving multi-agent, interactive human behavior and complex long-tail scenes at scale.

Currently, I’m on Tesla AI’s Autopilot team, working on Full Self-Driving (FSD) to contribute to real-world autonomy. Previously, I was a research intern at Applied Intuition, where I worked on large-scale, human-like self-play reinforcement learning, and at NEC Labs with Manmohan Chandraker, focusing on language-based, safety-critical simulation for autonomous driving.

I graduated from National Taiwan University. I worked in Bio-Inspired Robotics Lab as an undergrad researcher, advised by Prof. Pei-Chun Lin, we developed a Spherical Robotics System that with hybrid rolling and leaping capability.

News

• [Jun 2026] ECoSim is accepted to ECCV 2026!
• [May 2026] Joined Tesla AI's Autopilot team to contribute to real-world autonomy!
• [May 2026] Defended my dissertation, "Towards Scalable Simulation for Human-Centered Autonomy."
• [Apr 2026] Attended ICLR in Rio to present our paper SPACeR.

Publications

For the most up-to-date list of publications, please see google scholar.

ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation Yu-Hsiang Chen*, Wei-Jer Chang*, Yi-Ting Chen, Masayoshi Tomizuka European Conference on Computer Vision (ECCV), 2026 paper   website

HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic Yu-Hsiang Chen, Wei-Jer Chang, Christian Kotulla, Thomas Keutgens, Steffen Runde, Tobias Moers, Christoph Klas, Wei Zhan, Masayoshi Tomizuka, Yi-Ting Chen International Conference on Robotics and Automation (ICRA), 2026 paper   website

Self-Play Anchoring with Centralized Reference Models Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka, Yihan Hu, Wei Zhan International Conference on Learning Representations (ICLR), 2026 paper   website   blog

LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation Wei-Jer Chang, Wei Zhan, Masayoshi Tomizuka, Manmohan Chandraker, Francesco Pittaluga International Conference on Computer Vision (ICCV), 2025 paper   website

SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries Wei-Jer Chang, Francesco Pittaluga, Masayoshi Tomizuka, Wei Zhan, Manmohan Chandraker European Conference on Computer Vision (ECCV), 2024 paper   website

Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulation Wei-Jer Chang*, Chen Tang*, Chenran Li, Yeping Hu, Masayoshi Tomizuka, and Wei Zhan IEEE Robotics and Automation Letters (RA-L), 2023 paper