零散的知识，简短的观点，作为片段汇集于此。

graph TD
    全部
      
    click 全部 "/fragments/"
    

• Controllable Text-to-Image Generation with GPT-4
• High-Fidelity Generative Image Compression
• Image Coding for Machines with Omnipotent Feature Learning
• Rethinking Semantic Image Compression Representation with Cross-modality Transfer
• SMALLCAP -- Lightweight Image Captioning Prompted with Retrival Augmentation
• Tell Me What Happened -- Unifying Text-guided Video Completion via Multimodal Masked Video Generation
• Txt2Vid -- Ultra-Low Bitrate Compression of Talking-Head Videos via Text
• 在动态带宽下任务感知的分布式信源编码