影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
67.27/100
前 3.1%
全站排名 #2,004
发表论文16 篇
平均评分
年均产出5.3 篇/年
Chengzhi Mao
研究方向
Large Language Models · AI Interpretability and safety · Causal Inference · Robust Machine Learning · Computer Vision
16
LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
NeurIPS 2025Poster
三作26
Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
NeurIPS 2025Poster
通讯27
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
ICLR 2025Poster
通讯11
EditLord: Learning Code Transformation Rules for Code Editing
ICML 2025Poster
23
Emerging Tracking from Video Diffusion
ICLR 2025Withdrawn
通讯15
SPIN: Self-Supervised Prompt INjection
ICLR 2025Rejected
三作18
Learning to Rewrite: Generalized Detection of LLM-Generated Text
ICLR 2025Rejected
通讯19
PRUC & Play: Probabilistic Residual User Clustering for Recommender Systems
ICLR 2025Rejected
5
Taming Continuous Spurious Shift in Domain Adaptation
ICLR 2025Withdrawn
-1
Diversity Helps Jailbreak Large Language Models
ICLR 2025Withdrawn
通讯