AI ethics evidence index Search
Source-linked daily record
Evidence record 714 · automatically gathered

ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers

While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing sparse methods face a dilemma: dynamic pruning suffers from prohibitive runtime overhead and memory fragmentation, while static heuristics fail to capture fine-grained dependencies. In this work, we propose ScalingAttention, a training-free framework grounded in a key inductive bias: while individual activations are inp

Record details

Published: 22 June 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness

Physics-governed executable modelling of triboelectric nanogenerators

arXiv · 22 June 2026

Shared topic: Bias & fairness

The Unseen Hand: Manipulating Model Fairness and SHAP with Targeted Identity Re-Association Attacks

arXiv · 22 June 2026

Shared topic: Bias & fairness

Affective AI Safety: The Missing Piece in LLM Safety

arXiv · 22 June 2026

Shared topic: Bias & fairness

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation

arXiv · 23 June 2026

Shared topic: Bias & fairness

MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval

arXiv · 23 June 2026

Shared topic: Bias & fairness

FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation

arXiv · 23 June 2026

How to cite this record

ethics.ai (22 June 2026), “ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers,” evidence record 714, https://ethics.ai/record/714 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.