collaborators

6 papers

cs.AI2026

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

Lena Libon, Ben Rank, Jehyeok Yeon +5

As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such…

cs.AI2026

InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents

Jehyeok Yeon, Ben Rank, Maksym Andriushchenko

AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or narrow action spaces. Even no…

cs.LG2026

Graph-Regularized Sparse Autoencoders for LLM Safety Steering

Jehyeok Yeon, Federico Cinus, Yifan Wu +1

Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity objective treats latent features as indep…

cs.CR2026

Quantitative Certification of Agentic Tool Selection

Jehyeok Yeon, Isha Chaudhary, Gagandeep Singh

Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can…

cs.AI2026

Securing Multimodal AI through Internal Information Decomposition

Jehyeok Yeon, Hyeonjeong Ha, Qiusi Zhan +1

Multimodal large language models introduce attack surfaces absent in unimodal systems: adversaries can distribute malicious intent across modalities to evade unimodal safeguards. T…

cs.AI2025

TRAP: Targeted Redirecting of Agentic Preferences

Hangoo Kang, Jehyeok Yeon, Gagandeep Singh

Autonomous agentic AI systems powered by vision-language models (VLMs) are rapidly advancing toward real-world deployment, yet their cross-modal reasoning capabilities introduce ne…