Signals 4 · free daily AI digest

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper recorded by Signals 4 on 2026-09-17 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.LG · 机器学习 · first seen 2026-09-18

Abstract

Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appealing alternative and has been widely adopted in recent large language models, but directly applying it to video models often fails to preserve the fine-grained interactions required for high-quality generation. We present

Read on arXiv →

#10 most recent of 215 cs.LG papers we have recorded · ↑ newer: MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement · ↓ older: Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency
Cite this page: Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation: the #10 most recent of 215 cs.LG papers we have recorded (as of 2026-09-17). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/video-deltanet-a-video-native-hybrid-attention-for-livestream-video-generation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions