groundingLMM

★ 969

vs

shodh-memory

★ 314

groundingLMM vs shodh-memory

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.; shodh-memory: Shodh-Memory provides persistent, cognitive memory for AI agents, allowing them to retain context and learn across sessions. It's packaged as a single ~17MB binary that operates entirely offline on your hardware, preventing agents from forgetting information.