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:2512.23709v3 Announce Type: replace Abstract: Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due...
The paper introduces Relax Forcing, a training‑free memory mechanism for autoregressive video diffusion that structures temporal context into Sink, Tail, and History frames. By selecting History frames with a relaxation criterion, the method reduces error accumulation and attention overhead while preserving motion dynamics. Experiments on VBench‑Long demonstrate that this structured memory improves long‑video generation quality over existing baselines.
arXiv:2603.17825v2 Announce Type: replace Abstract: In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in vi...
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
arXiv:2602.19202v3 Announce Type: replace Abstract: Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensit...
Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth...
arXiv:2606. 29095v1 Announce Type: cross Abstract: 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 boundaries.
ZoomDiff is a high‑fidelity diffusion model designed to improve dual‑camera smooth zooming by producing photo‑realistic transitions. It strengthens dual‑image conditional guidance during denoising, injects flow‑aligned multi‑scale features from the VAE encoder into the decoder to recover high‑frequency details, and uses flow‑guided temporal consistency supervision to ensure smoother transitions. Experiments on synthetic and real‑world datasets show that ZoomDiff outperforms state‑of‑the‑art methods both quantitatively and qualitatively.
LiveVVT introduces a rolling streaming diffusion framework for video virtual try‑on that maintains high visual fidelity while enabling real‑time performance. It preserves bounded bidirectional modeling within a fixed‑size window, emits clean video chunks iteratively, and uses two memory modules—a bounded temporal memory and a persistent global appearance memory—to sustain long‑term consistency. A progressive distillation process further aligns teacher‑based bidirectional learning with causal few‑step inference, resulting in superior generation quality with 26× lower latency and 11× higher throughput compared to comparable models.
The paper introduces VoRTeC, a video compression framework that leverages a foundational flow model to encode latent video representations compactly and predict their positions along flow trajectories. By integrating multi‑scale priors and avoiding access to flow‑matching network parameters, VoRTeC achieves one‑step decoding with high perceptual fidelity, while maintaining temporal consistency through tail‑frame reuse and prior caching. Experiments show a 58% reduction in bit consumption compared to prior diffusion‑based methods and a decoding speed increase ranging from 3 to 197 times, reaching 13 FPS at 720p and 32 FPS at 480p.
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.
arXiv:2605. 16366v2 Announce Type: replace-cross Abstract: Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling.