Sangmin Woo
Sangmin Woo

Sangmin Woo

Applied Scientist @ AWS AI

Contact

  • sangminw [at] amazon.com

    shmwoo9395 [at] gmail.com

  • 2795 Augustine Dr, Santa Clara, CA 95054, United States

I am an Applied Scientist at AWS Agentic AI. I received my Ph.D. from KAIST.

Humans are inherently multi-modal learners: we naturally interact with and understand the world by seeing (vision), communicating and thinking (language), listening (audio), and acting with agency. I am passionate about advancing machine intelligence to mirror this ability, enabling systems to perceive, reason, and act in the world holistically.

My research interests include, but are not limited to:

  • Multi-modal AI: Vision + {Language, Audio, etc.} Multi-modal
  • Generative AI (LLMs, VLMs, Diffusion Models, etc.) Gen AI
  • Agentic AI (LLM Agents, VLAs, etc.) Agent
  • Visual Understanding Video Image

News

  • May 20261 paper accepted to TMLR 2026!
  • Jan 20262 papers accepted to EACL 2026 (1 Main, 1 Findings)!
  • Aug 20251 paper accepted to ESWA!
  • Aug 20251 paper accepted to EMNLP 2025 Main!
  • Jun 2025I am starting my new chapter at AWS Agentic AI! 🧑🏻‍💻
  • Jun 2025Selected as an Outstanding Reviewer at CVPR 2025!
  • May 20251 paper accepted to ACL 2025 Findings!
  • May 2025Successfully defended my PhD! 🎓
  • Apr 20251 paper accepted to CVIU!
  • Feb 20251 paper accepted to CVPR 2025!
  • Jan 20251 paper accepted to NAACL 2025 Main!
  • Dec 20241 paper accepted to AAAI 2025!
  • Sep 2024Excited to keep collaborating with the team remotely!
  • Sep 2024I had a fantastic summer internship with AWS Bedrock!
  • Jul 20243 papers accepted to ECCV 2024!
  • Jun 2024I joined AWS Bedrock as a summer intern!

Publications

* Equal contribution

2026

  • Multi-modalAgent

    StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks

    Ziyi Yin*, Sangmin Woo*, Kang Zhou, Sungyeon Kim, Aosong Feng, Haibo Ding, Luke Huan

    arXiv 2026

    PaperCodeProject

  • Agent

    An Empirical Study of Automating Agent Evaluation

    Kang Zhou*, Sangmin Woo*, Haibo Ding, Kiran Ramnath, Subramanian Chidambaram, Aosong Feng, Vinayak Arannil, Muhyun Kim, Ishan Singh, Darren Wang, Zhichao Xu, Megha Gandhi, Nirmal Prabhu, Soumya Smruti Mishra, Smeet Dhakecha, Vivek Singh, Gouri Pandeshwar, Lin Lee Cheong

    arXiv 2026

    PaperCodeBlog

  • Agent

    Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation

    Zhichao Xu*, Zongyu Wu*, Yun Zhou, Aosong Feng, Kang Zhou, Sangmin Woo, Kiran Ramnath, Yijun Tian, Xuan Qi, Weikang Qiu, Lin Lee Cheong, Haibo Ding

    TMLR 2026 KnowFM @ ACL 2026

    Paper

  • Agent

    Learning to Ideate for Machine Learning Engineering Agents

    Yunxiang Zhang, Kang Zhou, Zhichao Xu, Kiran Ramnath, Yun Zhou, Sangmin Woo, Haibo Ding, Lin Lee Cheong

    EACL 2026 Oral presentation

    Paper

  • Gen AI

    Diffusion Language Model Inference with Monte Carlo Tree Search

    Zheng Huang, Kiran Ramnath, Yueyan Chen, Aosong Feng, Sangmin Woo, Balasubramaniam Srinivasan, Zhichao Xu, Kang Zhou, Shuai Wang, Haibo Ding, Lin Lee Cheong

    EACL 2026 Findings

    Paper

2025

  • Video

    What and When to Look?: Temporal Span Proposal Network for Video Visual Relation Detection

    Sangmin Woo, Junhyug Noh, Kangil Kim

    ESWA 2025 IF 8.6

    PaperCode

  • Gen AI

    A Systematic Survey of Automatic Prompt Optimization Techniques

    Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong

    EMNLP 2025

    Paper

  • Gen AIMulti-modal

    Don’t Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models

    Sangmin Woo*, Donguk Kim*, Jaehyuk Jang*, Yubin Choi, Changick Kim

    ACL 2025 Findings

    PaperCodeProject

  • Multi-modalVideo

    Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition

    Sumin Lee, Sangmin Woo, Muhammad Adi Nugroho, Changick Kim

    CVIU 2025 IF 4.8

    Paper

  • Learning

    Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation

    Seokil Ham, Hee-Seon Kim, Sangmin Woo, Changick Kim

    CVPR 2025

    Paper

  • Gen AIMulti-modal

    Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models

    Sangmin Woo, Kang Zhou, Yun Zhou, Shuai Wang, Sheng Guan, Haibo Ding, Lin Lee Cheong

    NAACL 2025

    Paper

  • Gen AI

    Diffusion Model Patching via Mixture-of-Prompts

    Seokil Ham*, Sangmin Woo*, Jinyoung Kim, Hyojun Go, Byeongjun Park, Changick Kim

    AAAI 2025

    PaperCodeProject

2024

  • Gen AIMulti-modal

    RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models

    Sangmin Woo*, Jaehyuk Jang*, Donguk Kim*, Yubin Choi, Changick Kim

    arXiv 2024

    PaperCodeProject

  • Multi-modalVideo

    Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition

    Muhammad Adi Nugroho, Sangmin Woo, Sumin Lee, Jinyoung Park, Yooseung Wang, Donguk Kim, Changick Kim

    ECCV 2024

    Paper

  • Video

    Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition

    Sumin Lee, Yooseung Wang, Sangmin Woo, Changick Kim

    ECCV 2024

    Paper

  • Gen AI

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

    Byeongjun Park, Hyojun Go, Jinyoung Kim, Sangmin Woo, Seokil Ham, Changick Kim

    ECCV 2024

    PaperCodeProject

  • Gen AI

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

    Sangmin Woo*, Byeongjun Park*, Hyojun Go, Jinyoung Kim, Changick Kim

    CVPR 2024 Featured by Hugging Face Daily Papers Finalist, Qualcomm Innovation Fellowship 2024 Korea

    PaperCodeProjectDemo

  • Gen AI

    Denoising Task Routing for Diffusion Models

    Byeongjun Park*, Sangmin Woo*, Hyojun Go*, Jinyoung Kim*, Changick Kim

    ICLR 2024

    PaperCodeProject

  • Multi-modalVideo

    Sketch-based Video Object Localization

    Sangmin Woo, So-Yeong Jeon, Jinyoung Park, Minji Son, Sumin Lee, Changick Kim

    WACV 2024

    PaperCode

2023

  • Multi-modalVideo

    AHFu-Net: Align, Hallucinate, and Fuse Network for Missing Multimodal Action Recognition

    Muhammad Adi Nugroho, Sangmin Woo, Sumin Lee, Changick Kim

    VCIP 2023 Oral presentation

    Paper

  • Multi-modalVideo

    Multi-modal Social Group Activity Recognition in Panoramic Scene

    Donguk Kim, Sumin Lee, Sangmin Woo, Jinyoung Park, Muhammad Adi Nugroho, Changick Kim

    VCIP 2023

    Paper

  • Multi-modalVideo

    Cross-Modal Alignment and Translation for Missing Modality Action Recognition

    Yeonju Park, Sangmin Woo, Sumin Lee, Muhammad Adi Nugroho, Changick Kim

    CVIU 2023 IF 4.8

    Paper

  • Multi-modalVideo

    Audio-Visual Glance Network for Efficient Video Recognition

    Muhammad Adi Nugroho, Sangmin Woo, Sumin Lee, Changick Kim

    ICCV 2023 Invited Paper Talk @ CARAI Workshop

    Paper

  • Multi-modalVideo

    Towards Good Practices for Missing Modality Robust Action Recognition

    Sangmin Woo, Sumin Lee, Yeonju Park, Muhammad Adi Nugroho, Changick Kim

    AAAI 2023 Oral presentation

    PaperCode

  • Multi-modalVideo

    Modality Mixer for Multi-modal Action Recognition

    Sumin Lee, Sangmin Woo, Yeonju Park, Muhammad Adi Nugroho, Changick Kim

    WACV 2023

    Paper

2022 & earlier

  • Multi-modalVideo

    Explore and Match: Bridging Proposal-Based and Proposal-Free with Transformer for Sentence Grounding in Videos

    Sangmin Woo, Jinyoung Park, Inyong Koo, Sumin Lee, Minki Jeong, Changick Kim

    arXiv 2022 Finalist, 29th HumanTech Paper Award, Samsung Electronics Co., Ltd

    PaperCode

  • Image

    Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions

    Sangmin Woo, Junhyug Noh, Kangil Kim

    TNNLS 2022 IF 14.2

    PaperCode

  • Image

    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

    ICIP 2022

    Paper

  • Learning

    Impact of Sentence Representation Matching in Neural Machine Translation

    Heeseung Jung, Kangil Kim, Jong-Hun Shin, Seung-Hoon Na, Sangkeun Jung, Sangmin Woo

    Applied Sciences 2022 IF 2.8

    Paper

  • Learning

    Revisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs

    Sangmin Woo, Kangil Kim, Junhyug Noh, Jong-Hun Shin, Seung-Hoon Na

    Electronics 2021 IF 2.6

    PaperCode

Academic Service

Area Chair
ACL ARR (Oct 2025)
Conference Reviewer
ICLR (2024–), NeurIPS (2024–), ICML (2025–), AAAI (2023–) CVPR (2024–), ICCV (2025–), ECCV (2024–) ACL ARR (Jan 2026–)
Journal Reviewer
TPAMI (2025–), TNNLS (2023–), TMLR (2025–), TIP (2025–)

Awards & Honors

  • Jun 2025
    Outstanding Reviewer (711/12,593)IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Dec 2024
    Finalist ($1,000)Qualcomm Innovation Fellowship 2024 Korea
  • Oct 2023
    Invited Paper TalkCARAI Workshop, Center for Applied Research in Artificial Intelligence
  • Dec 2022
    Finalist29th HumanTech Paper Award, Samsung Electronics Co., Ltd.
  • Dec 2021
    Top Award ($10,000)LG Electronics Robot Contest, LG Electronics Co., Ltd.
  • Nov 2019
    Excellence Award ($500)Creative Space G A.I&IoT Makerthon, GIST