DocVQA

Researchers have discovered that Diffusion Multimodal Large Language Models (DMLLMs) reveal their valid semantic boundary at the first denoising step through a shift in MLP activation sparsity, enabli…

Microsoft researchers developed SkillOpt, a method that treats AI agent skill files as trainable parameters outside frozen target models, enabling controlled optimization through bounded text edits an…

The arXiv paper arXiv:2606.13317, submitted 11 Jun 2026, proposes SkillCAT, a training-free framework that converts LLM agent execution trajectories into reusable skills through three stages: Contrast…