Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
Zixuan Ren · Jinliang Lu · Junhong Wu · Yang Zhao · Dai Dai · hua wu · Haifeng Wang · Chengqing Zong
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。
Zixuan Ren · Jinliang Lu · Junhong Wu · Yang Zhao · Dai Dai · hua wu · Haifeng Wang · Chengqing Zong
Boyu Guan · Chuang Han · Yang Zhao · Chengqing Zong
Video-guided Machine Translation (VMT) seeks to enhance translation quality by incorporating contextual information derived from paired short video clips. However, many VMT samples are text-sufficient; even when visual information is needed, only minimal cues are required. Aiming to tackle these...
Chunyu Ye · Yunhao Zhang · Jingyuan Sun · Chong Li · Yang Zhao · Shaonan Wang
Decoding language from the human brain remains a grand challenge for Brain-Computer Interfaces (BCIs). Current approaches typically rely on unimodal brain representations, neglecting the brain’s inherently multimodal processing. Inspired by the brain’s associative mechanisms, where viewing an ima...