Diffusion Swallows the Decoder Too

Featured

• PhotoFlow: Agentic 3D Virtual Photography Missions score 10
  入选 HF Daily Papers; HF 热度: 24 upvotes (+4); 有代码实现; 关键词(3): agentic, reasoning, vision-language
• ETCHR: Editing To Clarify and Harness Reasoning score 9
  入选 HF Daily Papers; HF 热度: 12 upvotes (+3); 有代码实现; 关键词(3): fine-tuning, MoE, reasoning
• PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion score 8
  入选 HF Daily Papers; HF 热度: 36 upvotes (+4); 关键词(3): lightweight, latency, text-to-image
• Geo-Align: Video Generation Alignment via Metric Geometry Reward score 8
  入选 HF Daily Papers; HF 热度: 9 upvotes (+2); 有代码实现; 关键词(2): fine-tuning, synthetic data
• SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models score 8
  入选 HF Daily Papers; HF 热度: 14 upvotes (+3); 有代码实现
• LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws score 7
  入选 HF Daily Papers; HF 热度: 10 upvotes (+3); 关键词(3): scaling, quantization, fine-tuning
• Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers score 7
  入选 HF Daily Papers; HF 热度: 5 upvotes (+2); 有代码实现
• GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction score 7
  入选 HF Daily Papers; HF 热度: 10 upvotes (+3); 关键词(2): scaling, edge