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
21.21/100
前 38.7%
全站排名 #24,936
发表论文5 篇
平均评分
年均产出5.0 篇/年
Kun Yang
研究方向
multi-modal large language model · safety alignment · automous driving
18
Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
ICLR 2026Poster
二作17
Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs
ICLR 2026Poster
二作23
UpSafe℃: Upcycling for Controllable Safety in Large Language Models
ICLR 2026Rejected
6
MMOC: Multi-Model Online Collaboration Framework for Enhancing EEG Emotion Recognition
ICLR 2026Rejected
5
SEM: Reinforcement Learning For Search-Efficient Large Language Models
ICLR 2026Withdrawn
二作