Hi there! I'm Elea Zhong.

🔮 Intelligence Crafter. Engineer at @wand_app. Dev for @pixray. USC ✌️ class of '25 majoring in Computer Science.

I can:

🦾 Deploy deep learnings solutions for applications at scale
⚛️ Develop full-stack applications with Django, Flask, and React.js
🤖 Conduct academic research in deep learning and computer vision
🖼 Create art using and develop code enhancing creative AI models

Find me on:

Twitter

Github

Check out my resume (as of 2023. Jan):

>

Elea Zhong's Resume.pdf87.3KB

I’m part of:

wand© - Multiply your mind™

wand.earth

pixray

pixray demo notebooks Jupyter Notebook 8 4 Forked from BachiLi/diffvg Differentiable Vector Graphics Rasterization Python 4 People This organization has no public members. You must be a member to see who's a part of this organization. Most used topics Loading... You can't perform that action at this time.

github.com

Neuralism

I believe in the potential of creativity in every human being - from the cave paintings prehistoric men has painted with minerals with their fingers to the renaissance reinvigoration of majestic sculpture and oil, all radiants the stunning infinite potential of the creative human mind. When have us stopped drawing?

www.neuralismai.com

NOT JUST ART

an NFT studio from the USC.

not-just.art

Ahmanson Lab

Polymathy values different ways of learning, knowing, and being, ranging from the written word to various modes of embodiment and creative practice. The Ahmanson Lab extends the Harman Academy's focus on integrative learning by offering students a space for experimentation, play, and creative exploration.

polymathic.usc.edu

Notable Projects:

AI Looking Glass: Lewis Carroll + AI Art

Introduction Genertaive Jabberwocky Essential Alice 1 /media/alice_ai_art_landing_page_2.mp4 2022-03-31T11:30:43-07:00 Curtis Fletcher 3225f3b99ebb95ebd811595627293f68f680673e 40426 11 book_splash 2022-04-19T16:28:08-07:00 Curtis Fletcher 3225f3b99ebb95ebd811595627293f68f680673e

scalar.usc.edu

dazhizhong/strotss - Replicate

👋 Do you have a model that needs a demo? Email us to request early access. In the meantime, check out thegetting started docs.

replicate.com

Docs for Pixray

a guide to pixray

dazhizhong.gitbook.io

🧚‍♀️Pixray Minter

mint NFTs with pixray in a single click

px.dazhizhong.com

Papers:

Dominic Rampas, Pablo Pernias, Elea Zhong, Marc Aubreville. Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces.

Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces

Conditional text-to-image generation has seen countless recent improvements in terms of quality, diversity and fidelity. Nevertheless, most state-of-the-art models require numerous inference steps to produce faithful generations, resulting in performance bottlenecks for end-user applications.

arxiv.org

Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces

Ruizhen Liu, Dazhi Zhong, Zhicong Chen. Disrupting Deepfakes and Face-Swap Autoencoders with Fine-tuned Adversarial Attacks

www.yau-awards.com

Ruizhen Liu, Dazhi Zhong, Zhicong Chen. DROMO: Distributionally Robust Offline Model-based Policy Optimization

DROMO: Distributionally Robust Offline Model-based Policy Optimization

We consider the problem of offline reinforcement learning with model-based control, whose goal is to learn a dynamics model from the experience replay and obtain a pessimism-oriented agent under the learned model. Current model-based constraint includes explicit uncertainty penalty and implicit conservative regularization that pushes Q-values of out-of-distribution state-action pairs down and the in-distribution up.

arxiv.org

DROMO: Distributionally Robust Offline Model-based Policy Optimization