Cite
Notes
Only stored in your browser.
Attribution
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
arXiv 2026
On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral
arXiv 2025
from 2 papers
Christos Thrampoulidis
Wenlong Deng
Xiaoxiao Li
Jiaming Zhang
Minghui Chen
Qi Zeng
Yi Ren
Yushu Li
Zixin Ding