ART
&
TECH
Jason Lee

JASON LEE

I graduated from UC Berkeley with a dual major in Computer Science and Art Practice, alongside the EECS Honors Program, a selective track designed to push engineers beyond the bounds of their own discipline and into broader intellectual territory.

While most of my peers stayed within a single discipline, I was among the few actively bridging CS and art, an intersection that remains largely underexplored, and the space that became my calling.

My vision is to bridge the worlds of art and technology. I believe we are on the edge of a new realm of entertainment, one built not just on LLMs, but on deeper, less explored fields like deep computer vision and reinforcement learning. The future of creative experience lies in systems that can perceive, adapt, and respond, not just generate.

Outside of work, I'm drawn to exploring cuisine and fine dining, hunting down collectibles, golf, and bouldering.

Art Practice

2023 — 2025
Wastelands 2

Wastelands 2

Acrylic on canvas · 2′ × 3′ · 2024
Wastelands 3

Wastelands 3

Acrylic on canvas · 2′ × 3′ · 2024
Wastelands 4

Wastelands 4

Acrylic on wood, silkscreen Lokta paper · 18″ × 12″ · 2024
Wastelands 5

Wastelands 5

Acrylic on wood · 18″ × 12″ · 2024
Sultry 1

Sultry 1

Acrylic on canvas, collage · 18″ × 12″ · 2023
Sultry 2

Sultry 2

Acrylic on canvas, collage · 18″ × 12″ · 2023
Sultry 3

Sultry 3

Acrylic on canvas, collage · 18″ × 12″ · 2023
Sultry 4

Sultry 4

Acrylic on canvas, collage · 18″ × 12″ · 2023
2020 — 2023
Pour

Pour

Gouache on wood · 2′ × 4′ · 2022
Cyanotype 1

Cyanotype 1

Cyanotype on watercolor paper · 7″ × 18″ · 2021
Cyanotype 2

Cyanotype 2

Cyanotype on watercolor paper · 7″ × 18″ · 2021
Cyanotype 3

Cyanotype 3

Cyanotype on watercolor paper · 7″ × 18″ · 2021
Hide 1

Hide 1

Hand-made pigments on paper · 8″ × 11″ · 2021
Hide 2

Hide 2

Hand-made pigments on paper · 8″ × 11″ · 2021
Stomach

Stomach

Ink on Washi paper · 2′ × 4′ · 2021
Sketch 1

Sketch 1

Alcohol markers and ink · 2020
Sketch 2

Sketch 2

Alcohol markers and ink · 2020
Sketch 3

Sketch 3

Alcohol markers and ink · 2020
Experiment

Experiment

Hand-made pigments on Washi paper · 2020
Woodprint

Woodprint

Woodblock print with ink · 2020
2018 — 2020
Glowstone

Glowstone

Collage, alcohol markers, pen · 8.5″ × 11″ · 2019
Head in the Clouds

Head in the Clouds

Collage, alcohol markers, pen · 8.5″ × 11″ · 2019
Insomnia

Insomnia

Collage, alcohol markers, pen · 8.5″ × 11″ · 2018
Turtle

Turtle

Collage, alcohol markers, pen · 8.5″ × 11″ · 2018
2015 — 2018
Graphite Work 1

Graphite Work 1

Graphite on paper · 12″ × 18″ · 2017
Graphite Work 2

Graphite Work 2

Graphite on paper · 12″ × 18″ · 2017
Graphite Work 3

Graphite Work 3

Graphite on paper · 12″ × 18″ · 2016
Graphite Work 4

Graphite Work 4

Graphite on paper · 12″ × 18″ · 2016
Watercolor

Watercolor

Watercolor on paper · 12″ × 18″ · 2015

Machine Learning

Reinforcement Learning PPO Behavioral Cloning

Dense Reward Generation for RL Fine-Tuning

Behavioral-cloning policies plateau from compounding distribution shift; RL fine-tuning can correct them but is bottlenecked by sparse, binary task-completion rewards. I extract waypoints from the BC encoder's own latent space to produce an unsupervised dense reward, then run PPO on top. The residual pipeline yields +7 points over BC on LIBERO-Spatial and trains 5x faster than sparse PPO while preserving pretrained behavior.

View Project →
LoRA World Models V-JEPA2

Energy Landscape Analysis of LoRA on V-JEPA2-AC

Applied Low-Rank Adaptation to Meta's V-JEPA2-AC video world model for robotic manipulation on DROID-100. Measured energy landscapes before and after fine-tuning across 30 held-out trajectories. LoRA caused representation collapse: flat, non-discriminative landscapes, despite the technique's success on LLMs. A reminder that parameter-efficient methods designed for discrete token prediction don't transfer cleanly to continuous-valued latent spaces.

View Project →
Computer Vision Pyramids Alignment

Images of the Russian Empire

Reconstructed full-color images from Prokudin-Gorskii's early 20th-century glass-plate photographs by aligning separate R, G, and B exposures. Implemented multi-scale pyramid search with normalized cross-correlation to handle large offsets efficiently, then refined with edge-based alignment for the trickiest plates.

View Project →
Image Filters Fourier Hybrid Images

Filters & Frequencies

Explored frequency-domain image analysis through edge detection, Difference-of-Gaussians filters, and hybrid images that shift subject as viewing distance changes. Built seamless multi-resolution blending with Gaussian and Laplacian stacks to composite disparate images into a single coherent scene.

View Project →
Delaunay Image Warping Morphing

Face Morphing

Built a face-morphing pipeline that transitions between two portraits via manual correspondence points and Delaunay triangulation. Extended the work to compute the mean face of a population, extrapolate caricatures, and transfer shape and appearance across demographic groups.

View Project →
Generative AI Diffusion UNet

Diffusion Models

Studied denoising, sampling, and image-to-image translation using Stability AI's pretrained DeepFloyd IF. Implemented classifier-free guidance, inpainting, and text-conditioned style transfer, then trained a custom single-step UNet denoiser from scratch on MNIST to understand the mechanics end-to-end.

View Project →