notes
12 个文件夹 · 0 篇笔记
- 2022_Flamingo_A_Visual_Language_Model_for_Few-Shot_Learning文件夹
- 2023_Making_LLaMA_SEE_and_Draw_with_SEED_Tokenizer文件夹
- 2024_Chameleon_Mixed-Modal_Early-Fusion_Foundation_Models文件夹
- 2024_Emu3_Next-Token_Prediction_is_All_You_Need文件夹
- 2024_Janus_Decoupling_Visual_Encoding_for_Unified_Multimodal_Understanding_and_Generation文件夹
- 2024_Show-o_One_Single_Transformer_to_Unify_Multimodal_Understanding_and_Generation文件夹
- 2025_BAGEL_Emerging_Properties_in_Unified_Multimodal_Pretraining文件夹
- 2025_Janus-Pro_Unified_Multimodal_Understanding_and_Generation_with_Data_and_Model_Scaling文件夹
- 2025_Orthus_Autoregressive_Interleaved_Image-Text_Generation_with_Modality-Specific_Heads文件夹
- 2026_DuoGen_Towards_General_Purpose_Interleaved_Multimodal_Generation文件夹
- 2026_InternVL-U_Democratizing_Unified_Multimodal_Models_for_Understanding_Reasoning_Generation_and_Editing文件夹
- 2026_Wan-Weaver_Interleaved_Multi-modal_Generation_via_Decoupled_Training文件夹