作者位次 #2/3ECCV 2026Poster
RobustRDP: Advancing Reaction Diagram Parsing via Synthetic-to-Real Data Scaling and Robustness-Oriented Training
Jianting Tang · zezhong wu · Linli 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。
Jianting Tang · zezhong wu · Linli Xu
Xiaokun Sun · zezhong wu · Zewen Ding · Linli Xu
Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches effectively enhance perception abilities, they primarily target...