Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

Smol2Operator: Post-Training GUI Agents for Computer Use

Training mRNA Language Models Across 25 Species for $165

Training Design for Text-to-Image Models: Lessons from Ablations

TRL v1.0: Post-Training Library Built to Move with the Field

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model internals. We propose SAERL, a data engineering framework for LLM reinforcement lear...

LeRobot v0.5.0: Scaling Every Dimension