by Yuming Yang Papers
3 papers found
Conference
Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation
Yi Lu, Wanxu Zhao, Xin Zhou et al.
COLM 2025paperarXiv:2504.18857
Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Shuo Li, Tao Ji, Xiaoran Fan et al.
ICLR 2025arXiv:2410.11302
11
citations
Pre-Trained Policy Discriminators are General Reward Models
Shihan Dou, Shichun Liu, Yuming Yang et al.
NEURIPS 2025arXiv:2507.05197
10
citations