LongCat-Next: Lexicalizing Modalities as Discrete Tokens（美团）
Beyond Language Modeling:An Exploration of Multimodal Pretraining
UNDERSTANDING VS. GENERATION: NAVIGATING OPTIMIZATION DILEMMA IN MULTIMODAL MODELS
MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer
**MiniT2I:A Minimalist Baseline for Text-to-Image Generation
ERNIE 5.0 Technical Report（百度）
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation