Byeongjun Park

Research Scientist
EverEx
byeongjun.prk[at]gmail.com

Education

[Mar. 2020 ~ Aug. 2025] : Ph.D. in School of Electrical Engineering @ KAIST.
[Mar. 2015 ~ Feb. 2020] : B.S. in School of Electrical Engineering @ KAIST - Graduated Cum Laude.
[Mar. 2013 ~ Feb. 2015] : Gyeongnam Science High School.

Work Experience

[Aug. 2025 ~ Present]: Research Scientist @ EverEx (Mandatory Military Service)
[Mar. 2018 ~ Aug. 2018]: AI Research Intern @ Koh Young Technology

I am actively looking for Research Scientist Positions (or equivalent roles), starting in Fall 2026.

Research Interests

Diffusion Model Architecture: Reimagine diffusion training as a multi-task learning, and introduce how to synergize the training of multiple denoising tasks. [ICLR’24] [ECCV’24] [AAAI’25]
3D/4D Generation: Create high-quality 3D/4D objects and scenes by using generative models such as GAN, diffusion, and RF models, and lifting them into neural scene representations, such as point clouds, NeRF, and 3DGS. [TPAMI’24] [CVPR’24] [CVPR’25] [ICCV’25a] [ICCV’25b]
Video Generation/Understanding: Recently, I am working on various applications in video generation and understandings, including controllable video generation and scalable VideoLLMs. [CVPR’26a] [CVPR’26b]

News

[Feb. 2026] Two papers (1 Main and 1 Findings) are accepted to CVPR 2026.
[Aug. 2025] I have joined EverEx as a research scientist.
[Jun. 2025] Two papers about 3D/4D Generation are accepted to ICCV 2025.
[May. 2025] I successfully defended my Ph.D. thesis.
[Feb. 2025] One paper about 3D Generation is accepted to CVPR 2025.
[Dec. 2024] One paper about Diffusion Model is accepted to AAAI 2025.
[Jul. 2024] One paper about Diffusion Model is accepted to ECCV 2024.
[Mar. 2024] One paper about Novel View Synthesis is accepted to TPAMI 2024.
[Feb. 2024] One paper about One-Image-to-3D is accepted to CVPR 2024.
[Jan. 2024] One paper about Diffusion Model is accepted to ICLR 2024.

Publications

* indicates equal contribution

CVPR

ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding

Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung, Jong Chul Ye

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

PDF Code Project Page

CVPR

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs

Hyungjin Chung, Hyelin Nam, Jiyeon Kim, Hyojun Go, Byeongjun Park, Seongsu Ha, Byung-Hoon Kim

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

PDF Code Findings Track

ICCV

VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling

Hyojun Go*, Byeongjun Park*, Hyelin Nam, Byung-Hoon Kim, Hyungjin Chung, Changick Kim

International Conference on Computer Vision (ICCV), 2025

PDF Code Project Page

ICCV

SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering

Byeongjun Park*, Hyojun Go*, Hyelin Nam, Byung-Hoon Kim, Hyungjin Chung, Changick Kim

International Conference on Computer Vision (ICCV), 2025

PDF Code Project Page CVPR 2025 Workshop on WorldModelBench

CVPR

SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis

Hyojun Go*, Byeongjun Park*, Jiho Jang, Jin-Young Kim, Soonwoo Kwon, Changick Kim

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

PDF Code Project Page

AAAI

Diffusion Model Patching via Mixture-of-Prompts

Seokil Ham*, Sangmin Woo*, Jin-Young Kim, Hyojun Go, Byeongjun Park, Changick Kim

AAAI Conference on Artificial Intelligence (AAAI), 2025

PDF Code Project Page

Patent

Method and Apparatus with Scene Flow Estimation

Youngjun Kwak, Taekyung Kim, Changick Kim, Byeongjun Park, Changbeom Park

US Patent (US20220301190A1), 2025

PDF

TPAMI

Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis

Byeongjun Park*, Hyojun Go*, Changick Kim

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

PDF OpenReview IF=20.8 (2024)

ECCV

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

Byeongjun Park, Hyojun Go, Jin-Young Kim, Sangmin Woo, Seokil Ham, Changick Kim

European Conference on Computer Vision (ECCV), 2024

PDF Code Project Page

CVPR

HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D

Sangmin Woo*, Byeongjun Park*, Hyojun Go, Jin-Young Kim, Changick Kim

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

PDF Code Project Page Demo Finalist, Qualcomm Innovation Fellowship 2024 Korea

ICLR

Denoising Task Routing for Diffusion Models

Byeongjun Park*, Sangmin Woo*, Hyojun Go*, Jin-Young Kim*, Changick Kim

International Conference on Learning Representations (ICLR), 2024

PDF OpenReview Code Project Page

WACV

Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Video

Byeongjun Park, Changick Kim

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024

PDF

ICIP

Temporal Flow Mask Attention for Open-Set Long-Tailed Recognition of Wild Animals in Camera-Trap Images

Jeongsoo Kim, Sangmin Woo, Byeongjun Park, Changick Kim

IEEE International Conference on Image Processing (ICIP), 2022

PDF

ICIP

Fine-Grained Multi-Class Object Counting

Hyojun Go, Junyoung Byun, Byeongjun Park, Myung-Ae Choi, Seunghwa Yoo, Changick Kim

IEEE International Conference on Image Processing (ICIP), 2021

PDF Code

Honors and Services

Finalist in Qualcomm Innovation Fellowship 2024 Korea @ Dec. 2024
Samsung Best Paper Award in IEIE Autumn Annual Conference @ Nov. 2021
National Academic Excellence Scholarship (Science and Engineering, Korea) @ 2016, 2017, 2018

Powered by Jekyll and Minimal Light theme.