Hugging Face Trending Papers

SQuad: Sub-Quadratic Attention Distillation for Efficient Video Generation

Read the original on Hugging Face Trending Papers →

Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, $\mathcal{O}(n^2)$, with the number of latent tokens $n$. For the task of video generation, the token count is large, so this term dominates runtime and memory, and thereby caps the resolution and duration we can generate.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

Hugging Face Trending Papers
6d ago

SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention

Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from block-level or cluster-level proxy scores, which can obscure fine-grained differences among keys and miss high contribution keys under aggressive sparsity.

Hugging Face Trending Papers
5d ago

CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets

Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (MMDiT) on hundreds of thousands to millions of paired \emph{(reference, composed-target)} examples, where each composed target is a synthesized image of the subject in a novel scene.

arXiv Machine Learning
Jul 2

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

arXiv:2601. 11641v3 Announce Type: replace-cross Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment.

By Yuxi Liu, Yipeng Hu, Zekun Zhang, Kunze Jiang, Kun Yuan
arXiv AI
Jun 19

StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation

arXiv:2606. 20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training.

By Guangda Liu, Yiquan Wang, Chengwei Li, Wenhao Chen, Jing Lin, Yiwu Yao, Danning Ke, Wenchao Ding, Jieru Zhao