Cite
Notes
Only stored in your browser.
Attribution
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
arXiv 2025
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
CREAM: Consistency Regularized Self-Rewarding Language Models
arXiv 2024
from 3 papers
Kai Wang
researcher
Mingjia Shi
Wangbo Zhao
Xuanlei Zhao
Yang You
Yuhao Zhou
Zekai Li
Zhangyang Wang
Chetan Bansal
Damian Borth