SEONGLAND

Welcome

Seonglae Cho

Research Scientist

Research scientist focused on LLM safety, interpretability, and steering. Building tools to understand and control language model behavior.

Scholar GitHub LinkedIn Twitter

News

2026.05CorrSteer accepted at ICML 2026
2026.05ASG accepted at ICML 2026 AIWILD
2026.05Tool Calling Probing accepted at ICML 2026 FAGEN Oral
2026.05AgentRoom accepted at ICML 2026 FAGEN
2026.05PaaT accepted at ICML 2026 FAGEN
2026.03ControlRL accepted at ICLR 2026 Trustworthy AI
2026.03Confidence Manifold accepted at ICLR 2026 Reliable Autonomy

Research Interests

LLM Safety Mechanistic Interpretability Sparse Autoencoders Steering Vectors Agent Summarization

Mindset

PhilosophyOptimistic Nihilism
ConsciousnessBundle Theory
PredictionStatistical Thinking, Techno Optimism
FutureTechnological Singularity, Culture War
PlanningGTD, RICE Framework
CreationFirst Principles Thinking
AttitudeCritical Thinking
ComputingExtended Church-Turing Thesis