3 papers
cs.CL2025
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
Ãmer Faruk Akgül, Yusuf Hakan Kalaycı, Rajgopal Kannan +2
Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have e…
cs.CL2025
Resa: Transparent Reasoning Models via SAEs
Shangshang Wang, Julian Asilis, Ãmer Faruk Akgül +4
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning…
cs.CL2025
Tina: Tiny Reasoning Models via LoRA
Shangshang Wang, Julian Asilis, Ãmer Faruk Akgül +3
How cost-effectively can strong reasoning abilities be achieved in language models? Driven by this fundamental question, we present Tina, a family of tiny reasoning models achieved…