影响力指数

35.77/100

前 18.1%

全站排名 #11,626

发表论文5 篇

平均评分5.5

年均产出2.5 篇/年

Yao Huang

MS student@Beihang University ·中国·OpenReview

研究方向

LLM Safety · Adversarial attack and defense

Unveiling the Basin-Like Loss Landscape in Large Language Models

ICLR 2026Poster

Towards Seed-Invariant Safety Alignment in Text-to-Image Models

ICLR 2026Withdrawn

STAIR: Improving Safety Alignment with Introspective Reasoning

Mitigating Overthinking in Large Reasoning Models via Manifold Steering

NeurIPS 2025Poster

Adaptive Strategy Evolution for Generating Tailored Jailbreak Prompts against Black-Box Safety-Aligned LLMs

ICLR 2025Rejected

合作者 (16)