How I Study AI - Learn AI Papers & Lectures the Easy Way

Surgical Post-Training: Cutting Errors, Keeping Knowledge

Intermediate

Wenye Lin, Kai HanMar 2arXiv

The paper introduces SPOT, a training recipe that fixes an AI model’s mistakes with tiny edits while keeping what it already knows well.

#Surgical Post-Training#SPOT#DPO

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

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers

Intermediate

Bin Yu, Shijie Lian et al.Jan 20arXiv

TwinBrainVLA is a robot brain with two halves: a frozen generalist that keeps world knowledge safe and a trainable specialist that learns to move precisely.

#Vision-Language-Action#catastrophic forgetting#Asymmetric Mixture-of-Transformers

Papers3

Surgical Post-Training: Cutting Errors, Keeping Knowledge

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

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers