ImageNet-FID Negatively Correlates With Text-to-Image

Featured

• FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation score 7
  入选 HF Daily Papers; HF 热度: 18 upvotes (+3); 关键词(2): lightweight, real-time
• DiffusionBench: On Holistic Evaluation of Diffusion Transformers score 9
  入选 HF Daily Papers; HF 热度: 10 upvotes (+3); 有代码实现; 关键词(1): text-to-image
• ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs score 7
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 有代码实现; 关键词(4): retrieval-augmented, RAG, agentic, reasoning
• Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning score 6
  入选 HF Daily Papers; HF 热度: 8 upvotes (+2); 关键词(3): reasoning, text-to-image, open-source

Also Worth Noting

• MotifGen: Spatiotemporal interpolation of misaligned satellite images via multi-source generative modeling, in an application to tropical cyclones score 3
  机构: INRIA
• FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation score 3
  入选 HF Daily Papers