Cite
Notes
Only stored in your browser.
Attribution
Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
arXiv 2026
Tina: Tiny Reasoning Models via LoRA
arXiv 2025
Resa: Transparent Reasoning Models via SAEs
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
from 4 papers
Willie Neiswanger
Enes Burak Bilgin
Julian Asilis
Ollie Liu
Rajgopal Kannan
Shangshang Wang
Viktor Prasanna
Deqing Fu
Yusuf Hakan Kalaycı