Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
Official codebase for the paper "WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction"
A local personal memory lab with programmable fractal search and evidence governance.
Open-source AI memory engine for agents: multimodal memory, temporal knowledge graphs, graph RAG, and evidence-backed long-term context.
Grounded perceptual memory for personalized agents: VLM grounding, specialist identity encoders, and a training-free in-model attention bank. Paper: arXiv:2608.28609
To associate your repository with the multimodal-memory topic, visit your repo's landing page and select "manage topics."