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
18.57/100
前 45%
全站排名 #28,999
发表论文5 篇
平均评分
年均产出1.7 篇/年
Qibing Ren
研究方向
large language model · safety alignment · jailbreak · adversarial attack · self supervised learning · safety and privacy for generative AI · trustworthy AI · adversarial robustness · data poisoning
25
When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
ICLR 2026Poster
一作13
Unintended Harmful Knowledge Elicitation Issue in Large Reasoning Models and a RL Solution
ICLR 2026Rejected
一作30
One RL to See Them All: Visual Triple Unified Reinforcement Learning
ICLR 2026Rejected