LinMorph proposes a learnable softmax‑to‑linear weight transformation for Video Diffusion Transformers, replacing traditional random initialization or manual weight reuse. By learning a shared morphism that maps each target Gated DeltaNet parameter to a combination of pretrained query, key, value, and output projections, it generates layer‑specific initializations that preserve pretrained knowledge. The method enables faster recovery and higher generation quality across pretrained Video DiTs, especially when applied to larger video scales after training on short, low‑resolution clips.
arXiv:2606.13971v3 Announce Type: replace Abstract: While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current pr...
arXiv:2610.10524v1 Announce Type: new Abstract: Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fe...
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.
The paper introduces VDOT++, a unified distillation framework for few-step video generation across text-to-video, image-to-video, and condition-based tasks. It extends the previous VDOT method by incorporating an asymmetric unbalanced optimal transport distillation that allows student tokens to carry less mass, and an α1 ground cost that uses a weighted median to preserve modes. The approach combines distribution matching with adversarial refinement and cross-scale distillation, achieving competitive performance on multiple video benchmarks with only four sampling steps.
Token-Budget Distillation (TBD) is a parameter‑efficient fine‑tuning framework that adapts video vision‑language models to a fixed token budget. It freezes the pretrained backbone, updates only LoRA adapters, and incorporates FlashVID visual token compression. TBD uses a dual‑path teacher‑student design with full‑token supervision and compressed student optimization, enabling the student to recover full‑token semantics while remaining efficient under aggressive token reduction.
arXiv:2603. 00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning.
Video DeltaNet (VDN) introduces a hybrid attention mechanism for video diffusion models, combining local Softmax attention with a bidirectional linear memory branch called Video Delta Attention (VDA). The design updates memory once per frame, uses separate output projections and learnable gates to balance the two branches, and employs a staged teacher‑alignment recipe to integrate the new pathway into pretrained models. When applied to MiniMax H3, VDN achieves a 14.5× speedup, completing 14.3‑second, 768p video denoising in 6.70 seconds on eight NVIDIA B200 GPUs compared to the 50‑step dense baseline.
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: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.
arXiv:2608. 12032v1 Announce Type: cross Abstract: Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow.
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
arXiv:2609.06712v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) achieve strong video generation quality, but their dense spatiotemporal self-attention scales quadratically with sequ...