Data science, career and other topics
10 August 2023
A systematic survey of what's broken in RLHF — from reward hacking to evaluation gaps — and what techniques can fix, supplement, or replace it for safer AI alignment.
10 August 2023
My review of the paper UniversalNER Targeted Distillation from Large Language Models for Open Named Entity Recognition
07 August 2023
My review of the paper Skeleton-of-Thought Large Language Models Can Do Parallel Decoding
03 August 2023
My review of the paper Tracking Anything in High Quality
31 July 2023
My review of the paper TabR Unlocking the Power of Retrieval-Augmented Tabular Deep Learning
27 July 2023
My review of the paper Meta-Transformer A Unified Framework for Multimodal Learning
