"Historical citations (PPO Schulman 1707.06347, InstructGPT 2203.02155, DPO Rafailov 2023 NeurIPS, DeepSeekMath GRPO 2402.03300, DeepSeek-R1 2501.12948, KTO/IPO/SimPO/ORPO)", "Callout 'empty ...
"Rewrote §3.3 + Q21 debate convergence: replaced Banach contraction story with proper consensus dynamics framework (Perron-Frobenius for linear averaging, fixed-point set for non-linear softmax case, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results