Tianle Cai

Self-improvement in LLMs is not automatic; the pathway to effective learning depends critically on the task structure and the nature of the feedback received.

Learning algorithms might excel in memorization but can falter in broader generalization, with RL outperforming SFT in transferring knowledge across contexts.

LLMs can dynamically adapt to new information at inference time without costly retraining, simply by tweaking the final projection matrix of their MLP blocks.