Jorge Diaz Chao
jdiazchao@berkeley.edu

I am a senior Physics and Computer Science student at UC Berkeley. I work with incredible mentors Konpat Preechakul, Yutong Bai and Alexei Efros at the intersection of Computer Vision and Machine Learning, fields I love for their deep connection to intelligence and their transformative potential.
I am particularly interested in models that discover structure directly from nature and building tools smart and intuitive enough to blend into everyday life as natural extensions of ourselves.
Featured


PaperBench — An open, MCP-native AI research database where agents continuously discover papers and update benchmarks. Effortlessly compare SOTA papers by any topic or task, with fully auditable updates you can trust.


iCloset — An AI-powered virtual wardrobe that understands your unique style, delivering personalized, context-aware outfit suggestions and actionable wardrobe insights for smarter shopping and sustainable fashion.
Projects
Quick MAML — A lightweight PyTorch Model-Agnostic Meta-Learning (MAML) training framework enabling intuitive experimentation and quick prototyping.


Apex Flight — Advanced model rocketry and flight simulation. Quaternion-based guidance for thrust vector control, non-pyro cargo and recovery modules, and custom avionics. A life changer.
Publications
Bridging the Physics Gap: The Necessity of Serial Computation in
Video Diffusion ModelsBridging the Physics Gap: The Necessity of Serial Computation in Video Diffusion Models
Jorge Diaz Chao✦, Konpat Preechakul✦, Yuxi Liu, Yutong Bai (2026)

Interactive Program Synthesis for Modeling Collaborative Physical Activities
from Narrated DemonstrationsInteractive Program Synthesis for Modeling Collaborative Physical Activities from Narrated Demonstrations
Edward Kim✦, Daniel He✦, Jorge Diaz Chao✦, Wiktor Rajca, Ruta Desai, Antti Oulasvirta, Sanjit Seshia, Björn Hartmann (2025)
Teaching
CS 280 — Graduate Computer Vision (Angjoo Kanazawa and Alexei A. Efros)
Teaching Assistant (Spring 2026)
CS 180 — Computer Vision and Computational Photography (Angjoo Kanazawa and Alexei A. Efros)
Teaching Assistant (Fall 2025)
Photography
























Since 2004
