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
50.38/100
前 8.4%
全站排名 #5,408
发表论文10 篇
平均评分
年均产出5.0 篇/年
Zi Liang
研究方向
Trustworthy AI · AI Security · Privacy of LLMs · Natural Language Processing · Dialogue system
37
United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
ICLR 2026Desk Rejected
三作24
The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution
ICLR 2026Poster
二作18
Decision Potential Surface: A Theoretical and Practical Approximation of LLM's Decision Boundary
ICLR 2026Rejected
一作13
Abnaolizer: An AI Agent for Converting Antibodies to Nanobodies
ICLR 2026Withdrawn
15
Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
NeurIPS 2025Spotlight
一作22
Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
NeurIPS 2025Poster
27
United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
NeurIPS 2025Rejected
三作11
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
ICML 2025Poster
一作29
New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes
ICLR 2025Rejected
三作29
Alignment-Aware Model Extraction Attacks on Large Language Models
ICLR 2025Rejected
一作