LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? Paper β’ 2605.08985 β’ Published 18 days ago β’ 21
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction Paper β’ 2604.27393 β’ Published 27 days ago β’ 76
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning Paper β’ 2509.24650 β’ Published Sep 29, 2025 β’ 11
VoxCPM Collection Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning β’ 5 items β’ Updated 2 days ago β’ 13
Data Science and Technology Towards AGI Part I: Tiered Data Management Paper β’ 2602.09003 β’ Published Feb 9 β’ 7
UltraData Collection Ultra Scale, Ultra Quality, Ultra Coverage β’ 10 items β’ Updated 2 days ago β’ 83