Berkley | 🍎 Paper Today I Read 🦔

[209] SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

google RL Berkley 2025Q1

[205] LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Berkley reasoning 2025Q1

[179] Aligning Large Multimodal Models with Factually Augmented RLHF

25min RL 2023Q3 MLLM Berkley