作者位次 #2/5ICLR 2026Poster· General Machine Learning / Representation Learning
UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
Zhibin Lan · Liqiang Niu · Fandong Meng · Jie Zhou · Jinsong Su
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。
Zhibin Lan · Liqiang Niu · Fandong Meng · Jie Zhou · Jinsong Su
Fangxu Yu · Ziyao Lu · Liqiang Niu · Fandong Meng · Jie Zhou
Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches predominantly train models to associate events with timestamps in the forward video only. This paradigm hinders VLMs fr...