影响力指数

48.76/100

前 9.2%

全站排名 #5,927

发表论文10 篇

平均评分5.3

年均产出3.3 篇/年

Zifan Wang

Researcher@Scale AI·美国·OpenReview

研究方向

Explainable Deep Learning · Adversarial Robustness

Reliable Weak-to-Strong Monitoring of LLM Agents

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

ICLR 2026Rejected

WebGuard: Building a Generalizable Guardrail for Web Agents

ICLR 2026Withdrawn

Aligned LLMs Are Not Aligned Browser Agents

ICLR 2025Poster

Uncovering Model Vulnerabilities With Multi-Turn Red Teaming

ICLR 2025Rejected

Validating Mechanistic Interpretations: An Axiomatic Approach

ICML 2025Poster

合作者 (20)

Matt Fredrikson

Saranya Vijayakumar

Chen Bo Calvin Zhang

Sean M. Hendryx