Education
KAIST 2021.9 ~ 2023.8
Daejeon, Korea
M.S. - Artificial Intelligence
-
Machine Learning and Artificial Intelligence Lab (MLAI)
Seoul, Korea
POSTECH 2016.3 ~ 2021.8
Pohang, Korea
B.S. - Computer Science
-
Achieved GPA 3.70, Major GPA 3.96 (4.3 scale) Magna Cum Laude
Publications
[arXiv] CostNav: A Navigation Benchmark for Cost-Aware Evaluation of Embodied Agents
Haebin Seong, Sungmin Kim, Minchan Kim, Yongjun Cho, Myunchul Joe, Suhwan Choi, Jaeyoon Jung, Jiyong Youn, Yoonshik Kim, Samwoo Seong, Yubeen Park, Youngjae Yu, Yunsung Lee
- CostNav shows that today's navigation benchmarks miss what actually matters for real-world deployment: economic viability, not just task success. Our testbed is the first to model the full cost-revenue lifecycle of delivery robots, revealing that optimizing for navigation success often fails to optimize for commercial viability.
Physical AI, Navigation, Autonomous Delivery Systems, Robotics Economics, Economic Cost-Driven Optimization, Benchmark
[ICLR 2026] D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
Suhwan Choi*, Jaeyoon Jung*, Haebin Seong*, Minchan Kim, Minyeong Kim, Yongjun Cho, Yoonshik Kim, Yubeen Park, Youngjae Yu, Yunsung Lee
- D2E (Desktop to Embodied AI) shows that desktop interactions, especially gaming, provide scalable pretraining for robotics. Using 1.3K+ hours of data created by pseudo-labeling internet scale youtube videos, D2E achieves 96.6% on LIBERO manipulation and 83.3% on CANVAS navigation, establishing desktop pretraining as a practical robotics paradigm.
Physical AI, Vision-Language-Action (VLA) model, Embodied AI, Inverse Dynamics Model (IDM)
[ICLR 2025] HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
Seanie Lee*, Haebin Seong*, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner, Yoshua Bengio, Juho Lee, Sung Ju Hwang
- We propose HarmAug, a data augmentation method that distills a large safety guard model into a smaller 435M-parameter model by generating harmful instruction-response pairs using LLMs, resulting in a model that matches or outperforms larger models in F1 score and AUPRC while significantly reducing computational costs.
Large Language Model (LLM), AI Safety, LLM Guardrails, Jailbreak, AI Red-Teaming
[ACL 2025] SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Seanie Lee*, Dong Bok Lee*, Dominik Wagner, Minki Kang, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang
- We propose SafeRoute, a binary router that distinguishes hard examples from easy ones. Our method selectively applies the larger safety guard model to the data that the router considers hard, improving efficiency while maintaining accuracy compared to solely using the larger safety guard model.
Large Language Model (LLM), AI Safety, LLM Guardrails
[NeurIPS 2025] FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
Seanie Lee*, Sangwoo Park*, Dong Bok Lee*, Dominik Wagner, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang
- FedSVD reduces LoRA's DP-SGD noise by using SVD reparameterization, improving stability and performance.
Differential Privacy, Federated Learning, LoRA
[AAAI 2026 Workshop] BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models
Isack Lee*, Haebin Seong*
- Large language models contain hidden ethical biases that attackers can exploit to jailbreak them, and this paper both reveals those vulnerabilities and introduces a lightweight defense that reduces such bias-driven safety failures.
Large Language Model (LLM), AI Safety, Jailbreak, Social Bias, AI for Social Good
Experience
Maum.ai 2025.03 ~ Current
Gyeonggi, Korea
WoRV (World Model for Robotics and Vehicle control)
Senior AI Research Scientist
- Pre-training and Post-training of Foundational Visual-Language-Action (VLA) Models, for autonomous driving and robotics manipulation
- Sim-to-Real Digital Twin Transfer of Foundational Models to Real-World Robots with ROS, Isaac-Sim, Omnigraph, PhysX, and Omniverse
- Key Manager of Data Collection and Processing Pipeline for Physical AI, also powering D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI. Ranked #2 in Huggingface Paper of the Day.
- Lead of Project Physical Data Factory, collecting and training bi-manual humanoid teleoperation data for industry usage
- Lead of Project CostNav: A Navigation Benchmark for Cost-Aware Evaluation of Embodied Agents. Presenting at CES.
Theori 2023.11 ~ 2025.03
Seoul, Korea
AI for Offensive Security
AI Engineer
- Consulting for AI Safety (Red-Teaming LLMs, Blue-Teaming with Guard Models)
- AI Agent framework for finding Security Vulnerabilities in Blackbox, Whitebox Web Applications
- Security consultant report generation with Retrieval-Augmented Generation(RAG) and LLM fine-tuning with custom datasets
- Trained custom fine-tuned models for various security tasks (Webpage Classification, PII Detection, CWE Classification, ...)
Lead of Project Xint Autopen: Offensive Security AI Engine of Xint
- AI Agents for Automated Pentesting and Web Crawling
- Automated Pentesting with AI Agents: IDOR, XSS, Open Redirect, Sensitive Page Detection by crawling and fuzzing blackbox web applications
- Autonomous Page and Component Analysis: Automatically discover and test web pages and components for a wide range of security issues, including unauthorized access to admin pages and privileged APIs.
CTF Player
- Engaged in various CTF (Capture-The-Flag) competitions, including DEFCON, as a member of teams "The Duck" and "Maple Mallard Magistrates".
- Achieved 1st place in DEFCON 2024.
Kakao 2021 Summer
Gyeonggi, Korea
Recommender Systems Dept. (Internship)
Recommender Systems Researcher & Developer
- Item-to-Item recommendation for KakaoStory similar post recommendation,
- using content-based(CB) and collaborative filtering(CF) with multi-armed bandit(MAB)
- User-to-Item recommendation for Kakaotalk birthday gift recommendation,
- using LinUCB contextual bandit with click log pLSI features as the context vector
Fitmedi (Fitcare) 2019.12 ~ 2020.6
Seoul, Korea
Mobile App Full Stack Developer
Backend Developer
- MicroService Architecture with seperate Auth, CRUD, Custom Logic server
- GraphQL API using Hasura(PostgreSQL CRUD) & Apollo(Custom Logic)
- JWT token generating Auth server with OAuth for naver, kakao, google, facebook
- AWS Elastic Beanstalk & AWS Lambda(Serverless) for auto scaling and load balancing
Frontend Developer
- React Native app targeting both iOS & Android
- GraphQL API using Apollo Client & graphql-codegen
- Designer Cooperation with Zeplin
- Google play console & Apple developer page experience up to production
Pibex: POSCO R&D Enterprise 2018.6 ~ 2018.8, 2019.2 ~ 2019.8
Pohang, Korea
Deep Machine Vision Dept.
Deep Learning Engineer
- Smart Factory Solution Development for Quality Assurance in POSCO products
- Training and Deployment of Image Classfication and Segmentation Models
- Deep Learning Production on Nvidia Jetson Xavier, Jetson Nano
- Made Windows compatible versions of Tensorflow C api, C++ api, TF Lite, PyTorch
Web App Developer
- Integrated Deep Learning Web Application for Image Annotation + Training/Inference
- Tensorflow & Keras, Redis, Flask, Apache, HTML Canvas
Naver 2017 Summer
Gyeonggi, Korea
Smart Store Platform Dept. (Internship)
Big Data Server Developer
- Big Data extraction & graph representation using Spark SQL & Apache Zeppelin
- Open Source Commit : expanded data download limit on Apache Zeppelin
- Hadoop, Hbase configuration and optimization regarding network topology
- Server programming using Java Spring & Scala
Honors and Awards
Hacking & Security
- DEFCON CTF | #1 on Quals, #1 on Finals [Maple Mallard Magistrates] 2024
- BSidesSF CTF | #1 [The Duck] 2024
- CCE (Cyber Conflict Excercise) | #1 [The Duckling] 2024
- DEFCON CarHackingVillage CTF | #4 [AUTOCRYPT] 2023
- DEFCON CTF | #26 on Quals [K-Students] 2021
- DEFCON CTF | #7 on Quals, #12 on Finals [koreanbadass] 2020
- DEFCON CTF | #3 on Quals, #9 on Finals [seoulplusbadass] 2019
- Codegate CTF | #1 on University Div. Finals [PLUS] 2019
- Plaid CTF | #3 [seoulplusbadass] 2019
- Google CTF | #4 on Quals [LeaveCat-PLUS] 2019
- Seccon CTF | #2 on International Quals [AsiaEasterns] 2019
- DEFCON CTF | #7 on Quals, #19 on Finals [KaisHack+PLUS+GoN] 2018
- Plaid CTF | #4 [KaisHack+PLUS+GoN] 2018
Skills
- Physical AI, Vision-Language-Action (VLA) Models, Embodied AI, ROS, Isaac-Sim, PhysX, Omnigraph, Omniverse
- Large Language Models, LLM Safety, AI Safety, Guard Models
- Artificial Intelligence, Machine Learning, Deep Learning, Generative AI, Reinforcement Learning, Decision Making, Meta Learning
- Hacking & Security
- Development & Management of Team Level Software Projects
- Server Configuration and Deployment
- Deep Understanding in how computers work
- Linux, Windows, Pytorch, Jupyter, Python, C/C++, HTML/CSS/JS/TS, SQL, Docker, AWS, ....
Interests
- Making the world a better place with technology
- Wide interest in almost every CS related topic : AI, ML, Web, Security, System, Network, ...
- Currently most interested in Robotics Foundational Models, AI Safety
Certifications
IELTS General Training (International English Language Testing System) 2025.01.19
- Scored 8.0 : Very Good User
- "The test taker has fully operational command of the language with only occasional unsystematic inaccuracies and inappropriate usage. They may misunderstand some things in unfamiliar situations. They handle complex and detailed argumentation well."
IELTS Academic (International English Language Testing System) 2023.07.01
- Scored 7.5 : Good User
- "The test taker has operational command of the language, though with occasional inaccuracies, inappropriate usage and misunderstandings in some situations. They generally handle complex language well and understand detailed reasoning."
New TEPS (Test of English Proficiency developed by Seoul National University) 2020.09.19
- Scored 519, percentile rank of 96.67%
- "Near-native level of English proficiency. A score at this level typically indicates the highest English proficiency for a non-native speaker. A test taker at this level is able to perform technical tasks required in a specialized field after short-term training."
Activities
Reviewer Experience at Conferences and Journals
WOW Labs: Responsible Ai for Social Good Board Member, 2025 ~
- Advancing economic mobility through responsible AI, inclusive hiring, and equitable workforce innovation.
Postech Laboratory for Unix Security (PLUS) Certified Member, 2017 ~
- PLUS is an undergraduate cyber-security study club at Pohang University of Science and Technology (POSTECH).
- PLUS has competed in several domestic and international cyber-security(CTF) competitions since 1992.
Postech Decentralized Autonomous Organization (PDAO) Founding Member, 2022 ~
- PDAO is a blockchain community and open-source foundation based at POSTECH, designed as a Decentralized Autonomous Organization (DAO) to promote blockchain development, research, and education.
- PDAO operates through the PDAO Chain, a multi-chain governance platform, and focuses on community building, open-source projects, and integrating cryptocurrency into university operations.