影响力指数

-/100

发表论文2 篇

平均评分3.2

年均产出2.0 篇/年

Hyunjun Kim

Intern@EPFL·瑞士·OpenReview

研究方向

AI Safety · RAG · AI · HCI

AgentHard: Hardening LLM-Agent Evaluation with a Taxonomy of Artifacts and Automated Cleaning

ICLR 2026Rejected

ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks

ICLR 2026Rejected

合作者 (15)

Pavlo Molchanov