Miran's site

Miran Heo

Hi, I'm Miran. I am a research scientist at Meta SuperIntelligence Labs.

My research focuses on fundamental challenges in video perception, especially modeling temporal dynamics in sequence data and leveraging multimodal learning to achieve a more comprehensive understanding of the visual world.

Before joining Meta, I completed my Ph.D. at Yonsei University and spent time at Adobe Research and NVIDIA Research working on video segmentation and video large language models.

Research Experience

Meta SuperIntelligence Labs, New York, NY Sep 2025 - present
- Research Scientist
NVIDIA Research, Taiwan (remote) Jul 2024 - May 2025
- Research Scientist Intern
Adobe Research, San Jose, CA May 2023 - Sep 2023
- Research Scientist Intern
Adobe Research, San Jose, CA (remote) Mar 2021 - Dec 2021
- Research Scientist Intern

Publications

Autoregressive Universal Video Segmentation Model

Miran Heo*, Sukjun Hwang*, Min-Hung Chen, Yu-Chiang Frank Wang, Albert Gu, Seon Joo Kim, Ryo Hachiuma

preprint 2025

paper

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

Miran Heo, Min-Hung Chen, De-An Huang, Sifei Liu, Subhashree Radhakrishnan, Seon Joo Kim, Yu-Chiang Frank Wang, Ryo Hachiuma

CVPR 2025

paper / project page

Robust and Consistent Online Video Instance Segmentation via Instance Mask propagation

Miran Heo, Seoung Wug Oh, Seon Joo Kim, Joon-Young Lee

AAAI 2025

paper

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement

Hanjung Kim, Jaehyun Kang, Miran Heo, Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim

ECCV 2024

paper / code

A Generalized Framework for Video Instance Segmentation

Miran Heo, Sukjun Hwang, Jeongseok Hyun, Hanjung Kim, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim

CVPR 2023

paper / code

VITA: Video Instance Segmentation via Object Token Association

Miran Heo*, Sukjun Hwang*, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim

NeurIPS 2022

Ranked #3 in LSVOS Challenge at CVPR 2022

paper / code

Integrating Pose and Mask Predictions for Multi-person in Videos

Miran Heo, Sukjun Hwang, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim

CVPR Efficient Deep Learning for Computer Vision Workshop 2022

paper / project page

Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos

Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim

CVPR 2022

paper / code

Video Instance Segmentation using Inter-frame Communication Transformers

Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim

NeurIPS 2021

paper / code

Polygonal Point Set Tracking

Gunhee Nam, Miran Heo, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim

CVPR 2021

paper / code

Awards & Honors

Best PhD Dissertation Award, College of Computing, Yonsei University, Jul 2025
Yonsei Young Researcher Fellowship (Top 2 students in CS department), Jan 2024
Google Student Travel Grants (CVPR 2023)
The 3rd Place in Track 2 of the 4th Large-scale Video Object Segmentation Challenge (CVPR 2022)

Reviewer Service

Conference: CVPR (2021 ~) / ICCV (2021 ~) / ECCV (2022 ~) / WACV (2023 ~) / NeurIPS (2023 ~)
Journal: IJCV, TPAMI

US Patent

Generating Segmentation Masks for Objects in Digital Videos using Pose Tracking Data