Ming-Omni: A Unified Multimodal Model for Perception and Generation Paper โข 2506.09344 โข Published Jun 11, 2025 โข 31
view article Article nanoVLM: The simplest repository to train your VLM in pure PyTorch +5 ariG23498, lusxvr, andito, sergiopaniego, merve, pcuenq, reach-vb โข May 21, 2025 โข 263
An Empirical Study of GPT-4o Image Generation Capabilities Paper โข 2504.05979 โข Published Apr 8, 2025 โข 64