作者位次 #6/7ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
Ming Wen · Kun Yang · Xin Chen · Jingyu Zhang · DINGDING HAN · shiwen cui · Yuedong Xu
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Ming Wen · Kun Yang · Xin Chen · Jingyu Zhang · DINGDING HAN · shiwen cui · Yuedong Xu
Jingyu Zhang · Kun Yang · Ming Wen · Zhuoer Xu · Zeyang Sha · shiwen cui · Zhaohui Yang
Chenlong Yin · Zeyang Sha · shiwen cui · Changhua Meng · Zechao Li
Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building agents that ”think then act”. However, recent observations, like OpenAI’s o3, suggest a paradox: stronger reasoning often coincides with increased hallucination, yet no prior work has systematicall...