arXiv:2606. 09056v1 Announce Type: cross Abstract: Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths.
arXiv:2610.00686v1 Announce Type: new Abstract: Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene...
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...
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.
VideoTok4D introduces a 4D‑aware video tokenizer that transforms videos into compact tokens representing a dynamic 3D world. It employs spatiotemporal disentanglement to separate static and dynamic content, a track‑aware dynamic attention mechanism for motion consistency across views, and a diffusion prior (Co4DGen) for efficient 4D scene generation. Experiments show state‑of‑the‑art results with up to four orders of magnitude less storage than dense 4D representations, and shorter diffusion sequences for faster generation.
arXiv:2607.14088v2 Announce Type: replace Abstract: Video generation models typically rely on 3D-VAEs trained for pixel-level reconstruction, whose latent spaces may underrepresent semantic structure...
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:2608.20473v1 Announce Type: new Abstract: Video language models process videos as dense visual-token sequences with substantial representational redundancy. Compressing these sequences is there...
arXiv:2608.20515v1 Announce Type: new Abstract: Generative video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference...
arXiv:2603.17546v2 Announce Type: replace Abstract: Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptua...
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.