LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? Paper • 2605.08985 • Published May 9 • 24
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction Paper • 2604.27393 • Published Apr 30 • 71
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 71
