visual-language

Built a light-based visual language that AI systems can use intentionally for communication.

This paper introduces RINO (RGB In and RGB Out), a unified framework that represents diverse visual information (masks, depth, etc.) as RGB images and converts visual tasks into RGB-to-RGB image editing, enabling a single model to perform zero-shot transfer across tasks.

A guide on using AI to generate diagrams from academic papers by defining a personal visual language, using Draw.io templates, and building a custom AI skill for better paper comprehension.

This paper defines multi-image implicit toxicity (MIIT), where individually benign images become toxic when combined, and proposes MiShield, a model trained with progressively distilled reasoning supervision to detect MIIT. Experiments show MiShield-8B outperforms existing moderation services.