SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 125
Read-up research papers
-
-
S^2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Paper • 2502.12853 • Published • 29 -
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Paper • 2503.05592 • Published • 27 -
Self-Taught Self-Correction for Small Language Models
Paper • 2503.08681 • Published • 16 -
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper • 2405.21060 • Published • 68