Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits the diversity of images, and for person-centric prompts, can reflect or amplify demographic skew. We formalize this problem as coverage of a predefined set of semantically specified modes, which we call target-mode coverage. We then propose multi-axis max@K, a group-based reinforcement learning objective for improving such coverage in diffusion-based T2I models. Given a group of samples and one score per ta
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Multi-Axis Max@K Reinforcement Learning for Representative D” ≈ “Tongyi-MAI/Z-Image-Turbo””
- PossiblePossibly related (embedding) · 46%DiffusionGemma: 4x faster text generation →
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Multi-Axis Max@K Reinforcement Learning for Representative D” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Ku Onoda →
“Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Paavo Parmas →
“Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Hiroki Furuta →
“Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Soichiro Nishimori →
“Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation”
- LinkedLinked via arxiv author · 85%Yuta Oshima →
“Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation”