CORTEXA
← Browse
arxivcs.LGcs.CV2026-07-14

The Seriality Gap in Video Diffusion Models

Jorge Diaz Chao, Konpat Preechakul, Yuxi Liu, Yutong Bai

When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard-sphere dynamics, we find that the performance of standard bidirectional video diffusion degrades as the causal chain lengthens, even when provided more denoising steps. In a length-matched single-ball control, where ball-ball interactions are absent, the degradation largely disappears, isolating dependent-event structure rather than video length as the cause. Across intervention studies, methods that increase effective serial computation improve performance disproportionately, including autoregressive/blockwise generation and architectural depth. We identify this pattern as the seriality gap: a mismatch between tasks requiring growing serial computation and video diffusion models whose denoising loop does not provide scalable serial compute. We then prove that, for deterministic video prediction, denoising steps do not add serial computation beyond the backbone, indicating a structural obstacle for video diffusion on serial reasoning and simulation tasks.

View free PDFSource page

Related papers

arxivcs.LGcs.CV2026-07-07

FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models

Bowen Xue, Zihan Min, Xingyang Li, Zhekai Zhang, Haocheng Xi, Lvmin Zhang, et al.

Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footpr…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-03

HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

Dongyeun Lee, Amir Zandieh, Vahab Mirrokni, Junmo Kim, Insu Han

Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundamentally constrained by the quadratic complexity of the self-attention mechanism. Recent clustering-ba…

View free PDFSource page
arxivcs.CVcs.GRcs.LG2026-06-27

HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

Jing Yang, Mayoore Jaiswal, Zian Wang, Steven Zeng, Rochelle Pereira, Yajie Zhao, et al.

Diffusion-based video relighting enables controllable relighting from a single input video, but modern video diffusion backbones are trained on short clips and applied to long-horizon videos through chunked sliding-window inference, often causing temporal discontinuities at chunk…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-04

Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis

Haksoo Lim, Myeongjin Lee, Wonjoon Chang, Jaesik Choi

Diffusion models have achieved remarkable success across diverse domains, with performance closely related to the denoising backbones that parameterize the score function. In this paper, we present a systematic, phase-aware analysis of diffusion components and show that abrupt, e…

View free PDFSource page
arxivcs.CVcs.LG2026-07-07

Gen4U: Unifying Video Generation and Understanding via Diffusion

Michael King, Aravindh Mahendran, Matthew Koichi Grimes, Fedor Kitashov, Adham Elarabawy, Pedro Velez, et al.

Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual…

View free PDFSource page