Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learning What to Imitate: Entropy-Aware Distribution Mixing
Juan Garcia Giraldo, Matteo Santelmo, Eduard Durech +3
Small language models are often post-trained as students on reasoning traces from stronger teacher models to efficiently learn new skills. However, token-level imitation on traces…
cs.LG2026
SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
Alexis Limozin, Eduard Durech, Torsten Hoefler +2
Recent mixed-policy optimization methods for LLM reasoning that interleave or blend supervised and reinforcement learning signals report improvements over the standard SFT-then-RL…