is common in several AI and machine learning projects recently updated or discussed:
: A benchmark paper released by MLCommons (December 2025) that discusses security and "jailbreaking" techniques for Vision-Language Models (VLMs) and LLMs.
: A recent release from Hugging Face (March 2026) that focuses on scaling dimensions for AI robotics. The corresponding LeRobot paper has been accepted to ICLR 2026 .