一作ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
Mordal: Automated Pretrained Model Selection for Vision Language Models
Shiqi He · Insu Jang · Mosharaf Chowdhury
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。
Shiqi He · Insu Jang · Mosharaf Chowdhury
Shiqi He · Yue Cui · Xinyu Ma · Yaliang Li · Bolin Ding · Mosharaf Chowdhury
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical embodied reasoning in open web environments. However, exi...