作者位次 #6/8ECCV 2026Poster
ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction
Alen Mrdovic · Qingze Liu · Danrui Li · Mathew Schwartz · Kaidong Hu · Sejong Yoon · Mubbasir Kapadia · Vladimir Pavlovic
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。
Alen Mrdovic · Qingze Liu · Danrui Li · Mathew Schwartz · Kaidong Hu · Sejong Yoon · Mubbasir Kapadia · Vladimir Pavlovic
Changjun Park · Sejong Yoon · Jaekwang Kim
We propose DPLoRA (Dual-Pruning Low-Rank Adaptation), a framework that optimizes rank allocation via two stages: (1) an initial pruning stage (OPLoRA; Optimal Pruning LoRA) that uses Integer Linear Programming (ILP) to determine optimal layer-wise ranks without manual tuning; and (2) a progressiv...