Sotabase

Career

· PhD in Computer Science, Stanford University2025–
· Research Intern, NVIDIA Research2024–2025
· Visiting Researcher, Allen Institute for AI2022–2024
· Machine Learning Engineer, Hyperconnect2019–2022
· B.S. in Electrical and Computer Engineering, Seoul National University2017–2024
· Specialized High School Diploma, Seoul Science High School2014–2017

Publications (27)

Disentangling Label Distribution for Long-tailed Visual Recognition
Computer Vision and Pattern Recognition · 2020
292
cited
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Neural Information Processing Systems · 2024
249
cited
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Neural Information Processing Systems · 2024
140
cited
Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding
Interspeech · 2020
74
cited
Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics
North American Chapter of the Association for Computational Linguistics · 2024
44
cited
Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances
North American Chapter of the Association for Computational Linguistics · 2022
44
cited
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
2025
42
cited
MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning
Annual Meeting of the Association for Computational Linguistics · 2025
41
cited
AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
arXiv.org · 2024
33
cited
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
arXiv.org · 2025
33
cited
Measuring and Improving Semantic Diversity of Dialogue Generation
Conference on Empirical Methods in Natural Language Processing · 2022
22
cited
Champagne: Learning Real-world Conversation from Large-Scale Web Videos
IEEE International Conference on Computer Vision · 2023
21
cited
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models
NAACL-HLT · 2023
21
cited
Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning
arXiv.org · 2025
20
cited
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
arXiv.org · 2025
16
cited
Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
arXiv.org · 2025
16
cited
Representation Bending for Large Language Model Safety
Annual Meeting of the Association for Computational Linguistics · 2025
14
cited
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv.org · 2025
12
cited
Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation
Conference on Empirical Methods in Natural Language Processing · 2021
6
cited
Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms
Conference on Empirical Methods in Natural Language Processing · 2023
6
cited
Sotabase
Seungju Han | Researcher Profile | Sotabase | Sotabase