This post is the note of the paper “RAIN: Your Language Models Can Align Themselves without Finetuning”. See docs for more info.
This post is the note of the paper “PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding”. See docs for more info.
This post is the note of the paper “Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs”. See docs for more info.
