OMG-LLaVA: Unifying Vision and Language Understanding, Step-DPO for LLMs Mathematical Reasoning, MUMU's Multimodal Image Generation

AI Papers Podcast

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data Simulating Classroom Education with LLM-Empowered Agents SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation