Portrait
Hyojun Go
ELLIS PhD Student
ETH Zurich & Google
About Me

I am an ELLIS PhD student jointly between ETH Zurich (Photogrammetry and Remote Sensing group) and Google, advised by Prof. Konrad Schindler and Dr. Federico Tombari. I also work closely with Dr. Goutam Bhat and Dr. Prune Truong at Google. My research interests include generative models (especially Diffusion Models) and 3D generation.

Previously, I worked as a Research Scientist for my mandatory military service at Twelvelabs and Riiid (Korean military service companies). Prior to that, I received my M.S. degree from KAIST.

Research interests.

  • 3D Generation. My ultimate research goal is to generate and edit immersive 3D and 4D world scenes. Building on the power of generative models, I am interested in inducing scene geometry priors, representations, and physics into them.
  • Diffusion / Flow-based Models (Few-step Generation). Diffusion/flow models naturally lend themselves to multi-task learning, where a single model learns denoising across noise levels. I am interested in training strategies that encourage positive transfer between tasks to enable high-quality generation with fewer steps and lower compute.

Education
  • ETH Zurich
    ETH Zurich
    Ph.D. in 3D Generation (ELLIS, with Google)
    Apr. 2025 - present
  • KAIST
    KAIST
    M.S. in Electrical Engineering
    Mar. 2020 - Feb. 2022
  • Hanyang University
    Hanyang University
    B.S. in Electrical Engineering
    Mar. 2015 - Aug. 2019
Experience
  • Twelvelabs
    Twelvelabs
    Research Scientist (Mandatory military service) — Video Language Models (Pegasus-v1)
    Sep. 2023 - Mar. 2025
  • Riiid
    Riiid
    Research Scientist (Mandatory military service) — Diffusion Models
    Mar. 2022 - Aug. 2023
Invited Talks
  • Google Invited Talk
    Oct. 2025
  • AI Seoul Invited Talk — "Addressing Negative Transfer in Diffusion Models" (Seoul City Hall)
    Feb. 2024
News
2026
Two papers (one main, one Findings) accepted to CVPR 2026.
Feb 26
VIST3A accepted to ICLR 2026 as an Oral presentation.
Jan 22
2025
Two papers on 3D generation accepted to ICCV 2025.
Jun 15
One paper on 3DGS generation accepted to CVPR 2025.
Feb 15
One paper on Diffusion Models accepted to ICLR 2025.
Jan 15
2024
One paper on Diffusion Models accepted to AAAI 2025.
Dec 15
One paper on Diffusion Models accepted to ECCV 2024.
Jul 15
One paper on Novel View Synthesis accepted to TPAMI 2024.
Mar 15
Publications
2026
Understanding, Accelerating, and Improving MeanFlow Training
Understanding, Accelerating, and Improving MeanFlow Training

Jin-Young Kim*, Hyojun Go*, Lea Bogensperger, Julius Erbach, Nikolai Kalischek, Federico Tombari, Konrad Schindler, Dominik Narnhofer (* equal contribution)

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

[Paper]

Understanding, Accelerating, and Improving MeanFlow Training

Jin-Young Kim*, Hyojun Go*, Lea Bogensperger, Julius Erbach, Nikolai Kalischek, Federico Tombari, Konrad Schindler, Dominik Narnhofer (* equal contribution)

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

[Paper]

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs

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

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

[Paper] [Code]

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs

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

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

[Paper] [Code]

VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator
VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, Konrad Schindler

International Conference on Learning Representations (ICLR) 2026 Oral

[Paper] [Code] [Project]

VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, Konrad Schindler

International Conference on Learning Representations (ICLR) 2026 Oral

[Paper] [Code] [Project]

2025
SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering
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 (* equal contribution)

International Conference on Computer Vision (ICCV) 2025

[Paper]

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 (* equal contribution)

International Conference on Computer Vision (ICCV) 2025

[Paper]

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

International Conference on Computer Vision (ICCV) 2025

[Paper]

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 (* equal contribution)

International Conference on Computer Vision (ICCV) 2025

[Paper]

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

Hyojun Go*, Byeongjun Park*, Jiho Jang, Jin-Young Kim, Soonwoo Kwon, Changick Kim (* equal contribution)

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

[Paper] [Code] [Project]

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

Hyojun Go*, Byeongjun Park*, Jiho Jang, Jin-Young Kim, Soonwoo Kwon, Changick Kim (* equal contribution)

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

[Paper] [Code] [Project]

Denoising Task Difficulty-based Curriculum for Training Diffusion Models
Denoising Task Difficulty-based Curriculum for Training Diffusion Models

Jin-Young Kim*, Hyojun Go*, Soonwoo Kwon, Hyun-Gyoon Kim (* equal contribution)

International Conference on Learning Representations (ICLR) 2025

[Paper]

Denoising Task Difficulty-based Curriculum for Training Diffusion Models

Jin-Young Kim*, Hyojun Go*, Soonwoo Kwon, Hyun-Gyoon Kim (* equal contribution)

International Conference on Learning Representations (ICLR) 2025

[Paper]

Diffusion Model Patching via Mixture-of-Prompts
Diffusion Model Patching via Mixture-of-Prompts

Seokil Ham*, Sangmin Woo*, Jin-Young Kim, Hyojun Go, Byeongjun Park, Changick Kim (* equal contribution)

AAAI Conference on Artificial Intelligence (AAAI) 2025

[Paper] [Code] [Project]

Diffusion Model Patching via Mixture-of-Prompts

Seokil Ham*, Sangmin Woo*, Jin-Young Kim, Hyojun Go, Byeongjun Park, Changick Kim (* equal contribution)

AAAI Conference on Artificial Intelligence (AAAI) 2025

[Paper] [Code] [Project]

2024
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
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

[Paper] [Code] [Project]

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

[Paper] [Code] [Project]

TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models

Twelvelabs Team

Technical Report 2024

[Paper]

TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models

Twelvelabs Team

Technical Report 2024

[Paper]

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

Sangmin Woo*, Byeongjun Park*, Hyojun Go, Jin-Young Kim, Changick Kim (* equal contribution)

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

[Paper] [Code] [Project]

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

Sangmin Woo*, Byeongjun Park*, Hyojun Go, Jin-Young Kim, Changick Kim (* equal contribution)

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

[Paper] [Code] [Project]

Denoising Task Routing for Diffusion Models
Denoising Task Routing for Diffusion Models

Byeongjun Park*, Sangmin Woo*, Hyojun Go*, Jin-Young Kim*, Changick Kim (* equal contribution)

International Conference on Learning Representations (ICLR) 2024

[Paper] [Code] [Project]

Denoising Task Routing for Diffusion Models

Byeongjun Park*, Sangmin Woo*, Hyojun Go*, Jin-Young Kim*, Changick Kim (* equal contribution)

International Conference on Learning Representations (ICLR) 2024

[Paper] [Code] [Project]

Pegasus-v1 Technical Report
Pegasus-v1 Technical Report

Twelvelabs Team

Technical Report 2024

[Paper]

Pegasus-v1 Technical Report

Twelvelabs Team

Technical Report 2024

[Paper]

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

Byeongjun Park*, Hyojun Go*, Changick Kim (* equal contribution)

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

[Paper]

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

Byeongjun Park*, Hyojun Go*, Changick Kim (* equal contribution)

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

[Paper]

Multi-Architecture Multi-Expert Diffusion Models
Multi-Architecture Multi-Expert Diffusion Models

Yunsung Lee*, JinYoung Kim*, Hyojun Go*, Myeongho Jeong, Shinhyeok Oh, Seungtaek Choi (* equal contribution)

AAAI Conference on Artificial Intelligence (AAAI) 2024

[Paper]

Multi-Architecture Multi-Expert Diffusion Models

Yunsung Lee*, JinYoung Kim*, Hyojun Go*, Myeongho Jeong, Shinhyeok Oh, Seungtaek Choi (* equal contribution)

AAAI Conference on Artificial Intelligence (AAAI) 2024

[Paper]

2023
Addressing Negative Transfer in Diffusion Models
Addressing Negative Transfer in Diffusion Models

Hyojun Go*, JinYoung Kim*, Yunsung Lee*, Seunghyun Lee*, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi (* equal contribution)

Advances in Neural Information Processing Systems (NeurIPS) 2023

[Paper] [Code] [Project]

Addressing Negative Transfer in Diffusion Models

Hyojun Go*, JinYoung Kim*, Yunsung Lee*, Seunghyun Lee*, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi (* equal contribution)

Advances in Neural Information Processing Systems (NeurIPS) 2023

[Paper] [Code] [Project]

Evaluation of Question Generation Needs More References
Evaluation of Question Generation Needs More References

Shinhyeok Oh*, Hyojun Go*, Hyeongdon Moon, Yunsung Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi (* equal contribution)

Findings of the Association for Computational Linguistics (ACL) 2023

[Paper]

Evaluation of Question Generation Needs More References

Shinhyeok Oh*, Hyojun Go*, Hyeongdon Moon, Yunsung Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi (* equal contribution)

Findings of the Association for Computational Linguistics (ACL) 2023

[Paper]

Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Cross Encoding as Augmentation: Towards Effective Educational Text Classification

Hyun Seung Lee, Seungtaek Choi, Yunsung Lee, Hyeongdon Moon, Shinhyeok Oh, Myeongho Jeong, Hyojun Go, Christian Wallraven

Findings of the Association for Computational Linguistics (ACL) 2023

[Paper]

Cross Encoding as Augmentation: Towards Effective Educational Text Classification

Hyun Seung Lee, Seungtaek Choi, Yunsung Lee, Hyeongdon Moon, Shinhyeok Oh, Myeongho Jeong, Hyojun Go, Christian Wallraven

Findings of the Association for Computational Linguistics (ACL) 2023

[Paper]

Towards Practical Plug-and-Play Diffusion Models
Towards Practical Plug-and-Play Diffusion Models

Hyojun Go*, Yunsung Lee*, Jin-Young Kim*, Seunghyun Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi (* equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

[Paper] [Code]

Towards Practical Plug-and-Play Diffusion Models

Hyojun Go*, Yunsung Lee*, Jin-Young Kim*, Seunghyun Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi (* equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

[Paper] [Code]

2022
Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling
Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling

Yunsung Lee*, Gyuseong Lee*, Kwangrok Ryoo*, Hyojun Go*, Jihye Park*, Seungryong Kim (* equal contribution)

European Conference on Computer Vision Workshop (ECCVW) 2022

[Paper]

Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling

Yunsung Lee*, Gyuseong Lee*, Kwangrok Ryoo*, Hyojun Go*, Jihye Park*, Seungryong Kim (* equal contribution)

European Conference on Computer Vision Workshop (ECCVW) 2022

[Paper]

On the Effectiveness of Small Input Noise for Defending Against Query-based Black-box Attacks
On the Effectiveness of Small Input Noise for Defending Against Query-based Black-box Attacks

Junyoung Byun, Hyojun Go, Changick Kim

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

[Paper]

On the Effectiveness of Small Input Noise for Defending Against Query-based Black-box Attacks

Junyoung Byun, Hyojun Go, Changick Kim

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

[Paper]

Geometrically Adaptive Dictionary Attack on Face Recognition
Geometrically Adaptive Dictionary Attack on Face Recognition

Junyoung Byun, Hyojun Go, Changick Kim

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

[Paper]

Geometrically Adaptive Dictionary Attack on Face Recognition

Junyoung Byun, Hyojun Go, Changick Kim

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2022

[Paper]

2021
Fine-grained Multi-class Object Counting
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

[Paper]

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

[Paper]