Findings - a YedsonUQ Collection

YedsonUQ 's Collections

Survey

Distributed Training and Federated Learning

Uncertainty Quantification

Retrieval Augmented Generation (RAG)

Benchmark and Evaluation

Learning Paradigm/Scheme

Reinforcement Learning (RL)

Findings

updated 7 days ago

Large Language Models Think Too Fast To Explore Effectively

Paper • 2501.18009 • Published 11 days ago • 22
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 13 days ago • 101