image
📄 Paper Trending (67⬆️): Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation during denoising remains poorly understood. We introduce a causal interpretability framework for modern large-scale DiTs that combines attention decomposition with targeted interventions...
Fuente: HuggingFace_Papers
📄 Paper Trending (67⬆️): Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation during denoising remains poorly understood. We introduce a causal interpretability framework for modern large-scale DiTs that combines attention decomposition with targeted interventions...
No disponible
No disponible