Skip to content
View DylanWaken's full-sized avatar

Highlights

  • Pro

Organizations

@BlueHeavenAero

Block or report DylanWaken

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DylanWaken/README.md

title

 _  _  _    ___  _           ___  __   __ _       _    _  _    ___  _   _  _  _ 
| || |(_)  |_ _|( ) _ __    |   \ \ \ / /| |     /_\  | \| |  / __|| | | || \| |
| __ || |   | | |/ | '  \   | |) | \ V / | |__  / _ \ | .` |  \__ \| |_| || .` |
|_||_||_|  |___|   |_|_|_|  |___/   |_|  |____|/_/ \_\|_|\_|  |___/ \___/ |_|\_|

> Fundamental Entries_

█ Name:             Dylan Sun                      ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
█ At:               University of Southern California              ░░░░░░░░░░░░░
█ Learning:         Computer Science for Games                   ░░░░░░░░░░░░░░░
█ And like:         Concept art                         ░░░░░░░░░░░░░░░░░░░░░░░░
█ Doing Research:   [Computer Graphics] [Machine Learning]    ░░░░░░░░░░░░░░░░░░
█ Find me at:       [email protected]                                    ░░░░░░░░
____ INTRO _____|

     Hi, I am a Computer Science and Applied Mathematics student at the Univer-
sity of Southern California. I am currently doing researches in Computer Graphics
and Machine Learning. I am also interested in concept art and game design. For 
now, I am looking for opportunities to work in AI/CG labs and clubs

█ END OF BRIEF ◤◢◤◢◤◢◤◢◤◢◤◢◤◢◤◢◤◢

> Projects_

█ LEGEND : [▶] = Ongoing [■] = Ended, [▮▮] = Paused, [✪] = Pending

> Publications_

DEFORMABLE BETA SPLATTING (DBS). - SIGGRAPH 2025 - Co-First Author

VIT-LENS: TOWARDS OMNI-MODAL REPRESENTATIONS. - CVPR 2024

  • ViT-Lens aligns diverse novel modalities with pretrained Vision Transformers.
  • We achieved SOTA on multiple understanding, zero-shot text and image generation tasks.
  • Paper Link: https://arxiv.org/abs/2311.16081,

> Preferences_

> I mostly work on Linux Platforms (ubuntu-amd64)
> I code primarily in CUDA, C++, HLSL/GLSL, and Python
> My research focuses recently are:

- Physics Based Inverse Graphics
- Differentiable Volumetric Fields, Splats and Path Tracing
- Data Driven Real Time Procedural Generation

Pinned Loading

  1. DL_Memory_Palace DL_Memory_Palace Public

    The Obsidian Vault for all my deep learning knowledges, notes and labs

    Python 14

  2. Dylann Dylann Public

    A lightweight ML framework based on Cuda and CUDNN

    Cuda

  3. RayEngine RayEngine Public

    Ray Engine: A minimalistic header-only path tracer framework

    C++

  4. LibDylanRT LibDylanRT Public

    An experiment set of code for fundamental computer graphics

    C++

  5. Onesweep-RadixSort-CUDA-Implementation Onesweep-RadixSort-CUDA-Implementation Public

    A header only library for the implementations of the OneSweep CUDA radixsort algorithm

    Cuda 1

  6. SimpleLED SimpleLED Public

    A ws281x led controlling system based on raspi (server and client)

    C