EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
Text-to-image diffusion models power everyday creative tasks, but they still reproduce the demographic biases in their training data. On common prompts such as ``a photo of a nurse,'' ``a photo of a CEO'', they skew their outputs toward one gender, driven by the statistics of training data rather than anything in the text. Existing debiasing methods show promise in narrow settings but require retraining, batch-level control, or prompt-specific tuning, limiting their scalability. We propose \emph{EquiSteer}, a training-free method that works per sample by steering cross-attention (CA) activatio
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.
- LinkedLinked via unknownDiffusionGemma: 4x faster text generation →
- LinkedLinked via unknownattention-zoo →
- LinkedLinked via arxiv author · 85%Tatiana Gaintseva →
“EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation”
- LinkedLinked via arxiv author · 85%Akshit Achara →
“EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation”
- LinkedLinked via arxiv author · 85%Gregory Slabaugh →
“EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation”
- LinkedLinked via arxiv author · 85%Jiankang Deng →
“EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation”
- LinkedLinked via arxiv author · 85%Ismail Elezi →
“EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation”