Cite
Notes
Only stored in your browser.
Attribution
On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral
arXiv 2025
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
ICCV 2023 1
from 2 papers
Boying Gong
Christos Thrampoulidis
Kui Jia
Wenlong Deng
Xiaoxiao Li
Xun Xu
Yi Ren
Yongyi Su