VELR: Efficient Video Reward Feedback via Ensemble Latent Reward Models
Liyu Zhang · Kehan Li · Tao Zhou · Zeyi Huang · Chao LI · Jiming Chen
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。
Liyu Zhang · Kehan Li · Tao Zhou · Zeyi Huang · Chao LI · Jiming Chen
Binxing Xu · Hao Gu · Lujun Li · Hao Wang · Bei Liu · Jiacheng Liu · Qiyuan Zhu · Xintong Yang · Chao LI · Sirui Han · Yike Guo
Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and error accumulation across layers. To address these issues, we...
Xin Tang · Quanyan Gao · Chao LI
Lidi Zhang · Han Wu · Liyu Zhang · Ruofeng Liu · Haotian Wang · Chao LI · Desheng Zhang · Yunhuai Liu · Tian He