I’m Seanie Lee.
I study how to make
AI safer.
My research focuses on AI safety, responsible AI, and evaluation. I received my PhD in Artificial Intelligence from KAIST in 2026.
Work Experience
Apple
Research Intern · Machine Learning Research
Developed SimSAT, a synthetic training pipeline that helped tool-calling agents generalize to unseen APIs and user states on AppWorld and OfficeBench.
Paper: Simulate to Generalize
Host: Raviteja Vemulapalli
KRAFTON
Research Intern
Developed ThinkSafe, which uses self-generated safety data to improve the safety of reasoning models while keeping reasoning performance competitive.
Paper: ThinkSafe
Mila
Research Intern
Studied whether broader red-team coverage improves LLM safety tuning and found that it helped models withstand attacks outside the training set.
Paper: Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
Advisor: Yoshua Bengio
Collaborator: Minsu Kim
Collaborator: Moksh Jain
Collaborator: Esmeralda S. Whitammer
Apple
Research Intern
Built a lightweight conversation retriever for few-shot dialogue state tracking by distilling a model trained on conversation summaries.
Host: Anders Johannsen
Collaborator: Jianpeng Cheng
National University of Singapore
Research Intern · Remote
Used self-distillation to regularize continued transformer pretraining on domain-specific data, improving downstream classification in the evaluated vision and language tasks.
Paper: Self-Distillation for Further Pre-training of Transformers
Advisor: Kenji Kawaguchi
Education
-
2022–2026
-
2020–2022KAIST
MS in Artificial Intelligence
-
2011–2018Yonsei University
BA in Library and Information Science
Publications
-
Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models
SimSAT uses language models to simulate stateful APIs and generate training trajectories, helping agents generalize to unseen environments on AppWorld and OfficeBench.
-
Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition
Personalized adaptation and synthetic dysarthric speech improve speech recognition for speakers with dysarthria.
+ MORE − LESS Publications from 2020 to 2024
-
Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries
A lightweight retriever distilled from conversation summaries improves few-shot dialogue state tracking without generating summaries at inference time.
-
Margin-based Neural Network Watermarking
Margin-based watermarking strengthens ownership verification for neural networks against attempts to replicate their functionality.
-
Self-Supervised Set Representation Learning for Unsupervised Meta-Learning
Set-SimCLR learns representations of sets from unlabeled images and improves few-shot classification over instance-level self-supervision and unsupervised meta-learning baselines.
-
Set-based Meta-Interpolation for Few-Task Meta-Learning
Meta-Interpolation uses neural set functions to generate additional training tasks and improve adaptation when few source tasks are available.
-
On Divergence Measures for Bayesian Pseudocoresets
The paper connects dataset distillation to Bayesian pseudocoresets through reverse KL and Wasserstein objectives and unifies the two views.
-
Set Based Stochastic Subsampling
A two-stage subsampler combines coarse global context with sequential refinement to retain the input elements most useful for a downstream task.
-
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning
Sequential Reptile aligns gradients across language tasks during meta-training to improve multilingual transfer.
Honors and Awards
-
2023
-
2022
Google
Google Travel Grant for NeurIPS 2022
-
2019
Invited Talks
-
May 2025Korea University
Synthetic Data Generation for LLM Safeguards
Seminar · Seoul
-
Apr 2025Hanyang University
Synthetic Data Generation for LLM Safeguards
Seminar · Seoul
-
Oct 2023Nuremberg Institute of Technology Georg Simon Ohm
Tech talk
-
May 2023Samsung SDS
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
Tech talk
-
Dec 2020
NAVER
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs
Tech talk