groundingLMM: GLaMM (Grounding Large Multimodal Model) is an end-to-end trained LMM capable of generating natural language responses integrated with object segmentation masks, enabling visual grounding and versatile interaction with images at multiple granularity levels. It introduces the novel task of Grounded Conversation Generation (GCG), supports various downstream applications like referring expression segmentation and region-level captioning, and is underpinned by the large-scale GranD dataset.; estonian-mcp: The estonian-mcp project is a Model Context Protocol server that exposes the EstNLTK Estonian NLP toolkit as real-time tools for LLM clients. It provides ground truth for Estonian linguistics, helping LLMs avoid guessing on spelling, morphology, and offering genuine synonyms and editorial checks.
Interactive visual assistants that understand and respond to user queries about specific image regions.
Proofreading and correcting Estonian text for spelling, grammar, and orthography.