Research map / Image generation / Text-to-image diffusion
Intrinsic Concept Extraction Based on Compositional Interpretability
Hanyu Shi, Hong Tao, Guoheng Huang, Jianbin Jiang, Xuhang Chen, Chi-Man Pun, Shanhu Wang, Pan Pan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Hyperbolic Entailment Learning (HEL) to HCL (ablation) | HyperExpress · D1 dataset | SIM_I: 0.625 -> 0.688 | Improved |
| add Horosphere Projection (HP) to HCL (ablation) | HyperExpress · D1 dataset | ACC_1: 0.326 -> 0.348 | Improved |
| combine HCL, HEL and HP (ablation) | HyperExpress · D1 dataset | ACC_1: 0.348 -> 0.504 | Improved |
| add HEL and HP together to HCL (ablation) | HyperExpress · D1 dataset | SIM_I: 0.625 -> 0.699 | Improved |
| HyperExpress vs ICE | ICE · UCEBench | ACC_1: 0.325 -> 0.504 | Improved |
| HyperExpress vs ICE | ICE · UCEBench | SIM_I: 0.738 -> 0.699 | Hurt |
| HyperExpress vs ICE | ICE · ICBench | SIM_T-T object: 0.249 -> 0.280 | Improved |
Closest papers by meaning
- ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models (CVPR 2025 · similarity 0.94)
- Towards Compositionality in Concept Learning (ICML 2024 · similarity 0.90)
- ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models (AAAI 2024 · similarity 0.87)
- FACE: Faithful Automatic Concept Extraction (NeurIPS 2025 · similarity 0.86)
- Learning Vision and Language Concepts for Controllable Image Generation (ICML 2025 · similarity 0.85)
- The Hidden Language of Diffusion Models (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
