Papers2

#Log-Likelihood Ratio

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

The paper shows that a model that looks great after supervised fine-tuning (SFT) can actually do worse after the same reinforcement learning (RL) than a model that looked weaker at SFT time.

#Supervised Fine-Tuning#Reinforcement Learning#Distribution Mismatch

LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

Intermediate

Shijie Lian, Bin Yu et al.Jan 21arXiv

Robots often learn a bad habit called the vision shortcut: they guess the task just by looking, and ignore the words you tell them.

#Vision-Language-Action#Bayesian decomposition#Latent Action Queries