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
39.24/100
前 15%
全站排名 #9,630
发表论文7 篇
平均评分
年均产出2.3 篇/年
Changjiang Li
研究方向
Backdoor Attack · Adversarial Machine Learning · Trustworthy Machine Learning
16
When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
ICLR 2026Poster
17
Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
ICLR 2026Poster
二作16
MASpi: A Unified Environment for Evaluating Prompt Injection Robustness in LLM-Based Multi-Agent Systems
ICLR 2026Withdrawn