arXiv Computer Vision
Steering Video Diffusion Transformers with Massive Activations
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 30
Temporal-Attention Head Specialization During Video Diffusion Training
arXiv:2609.31654v2 Announce Type: replace-cross Abstract: Video diffusion transformers depend on temporal attention to coordinate information across frames, yet nearly everything known about this mec...
arXiv Machine Learning
Sep 18
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Video DeltaNet (VDN) introduces a hybrid attention mechanism for livestream video generation, combining local Softmax attention with a bidirectional linear memory branch called Video Delta Attention (VDA). VDA updates memory once per frame, integrating spatial tokens, while separate output projections and learnable gates balance the two branches. Applied to MiniMax H3, VDN achieves a 14.5× speedup over the dense baseline, completing 14.3‑second, 768p video denoising in 6.70 seconds on eight NVIDIA B200 GPUs.
arXiv Machine Learning
Sep 22
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms
arXiv:2609.23658v1 Announce Type: cross Abstract: Despite impressive visual quality, state-of-the-art video diffusion models often generate content that violates real-world physical laws. While exist...
arXiv Computer Vision
Aug 25
Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting
arXiv:2606.06158v2 Announce Type: replace Abstract: Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous...
arXiv AI
Aug 7
In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion
arXiv:2608. 05237v1 Announce Type: cross Abstract: Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame.
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.