paper-with-me

홈 › Papers

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

2026-09-17 · Haocheng Xi, Yiming Xie, Hexu Zhao, Yiwen Zhang, Michael Liu, Thomas Creavin, Kurt Keutzer, Xiuyu Li, Zhaoyang Lv, Chenfeng Xu, Haiwen Feng hf

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 Video DeltaNet (VDN), which combines local Softmax attention with bidirectional linear memory for long-range video context. Its linear branch introduces Video Delta Attention (VDA), which updates memory once per frame by jointly incorporating its spatial tokens. Separate output projections and learnable gates calibrate the two branches, while a staged teacher-alignment recipe progressively introduces the new pathway into pretrained models. We instantiate VDN on MiniMax H3, applying the hybrid to video-to-video interactions while retaining Softmax for interactions involving text or audio. With eight-step distillation and an optimized SGLang serving stack, VDN-H3 completes DiT denoising for a 14.3-second, 768p video in 6.70 seconds on eight NVIDIA B200 GPUs, corresponding to a 14.5x speedup over the 50-step dense H3 baseline on the same GPU count.

📄 PDF Abstract BibTeX arXiv:2609.20744

Code (3)

InsomaniacElf/sg-tamil-tts-resources- ★ 1
Valiant-Cat/hfpaper
liutaocode/Video-Generation-arxiv-daily ★ 19

Tasks

Video Generation

Similar Papers 제목 키워드 기반

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

2026-05-14 · Haoyi Zhu, Haozhe Liu, Yuyang Zhao, Tian Ye 외 arxiv

We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precise camera control. SANA-WM achieves vi…

Provably Shorter Scratchpads in Hybrid DeltaNet-Attention Decoders

2026-05-15 · Tomasz Steifer arxiv

We investigate the expressive power of hybrid recurrent-attention decoders, a class of architectures used in recent open-source language models such as Qwen3-Next and its successors. These models combine Gated Attention …

One-Minute Video Generation with Test-Time Training

2025-04-07 · CVPR 2025 1 · Karan Dalal, Daniel Koceja, Gashon Hussein, Jiarui Xu 외

Transformers today still struggle to generate one-minute videos because self-attention layers are inefficient for long context. Alternatives such as Mamba layers struggle with complex multi-scene stories because their hi…

MambaVideo Generation

Parallelizing Linear Transformers with the Delta Rule over Sequence Length

2024-06-10 · Songlin Yang, Bailin Wang, Yu Zhang, Yikang Shen 외

Transformers with linear attention (i.e., linear transformers) and state-space models have recently been suggested as a viable linear-time alternative to transformers with softmax attention. However, these models still u…

Language ModelingLanguage ModellingMambaState Space Models

Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing

2026-07-08 · Tommaso Cerruti, Tim Rieder, George Rowlands, Lingfeng Jin 외 arxiv

Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context. This paper presents a comparative study of softmax atten…