arXiv AI
Directional Attention Guidance for Diffusion Models via Sparse Hopfield Retrieval
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 2
Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning
arXiv:2610.01723v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable progress in image synthesis, yet can exhibit memorization by closely reproducing individual tra...
arXiv Computer Vision
Sep 1
EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance
arXiv:2512.17303v3 Announce Type: replace Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free gu...
arXiv AI
Jun 15
Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing
arXiv:2606. 14125v1 Announce Type: cross Abstract: Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preservation.
arXiv Machine Learning
Sep 24
Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models
The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
arXiv AI
Jun 2
You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
arXiv:2603. 00133v2 Announce Type: replace-cross Abstract: Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement.
arXiv AI
Sep 30
On Trajectory-Aware Training for Masked Diffusion Language Models
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...