OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning andUnderstandingStep-DPO: Step-wise Preference Optimization for Long-chain Reasoning ofLLMsMUMU: Bootstrapping Multimodal Image Generation from Text-to-Image DataSimulating Classroom Education with LLM-Empowered AgentsSeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval AugmentedGeneration
Podchaser is the ultimate destination for podcast data, search, and discovery. Learn More