Token merging is an effective approach to reducing KV-cache memory consumption in autoregressive video generation by clustering temporally redundant tokens and retaining only a small set of representa...
CORAL-KV is a new framework for compressing the key‑value (KV) cache used by autoregressive video diffusion models. It predicts keys and values across cache layers using block‑diagonal‑plus‑low‑rank (block‑DPLR) predictors, then quantizes only the residuals, offering a flexible trade‑off between fidelity and memory usage. In extensive tests on HY‑WorldPlay and MAGI‑1, the reusable configuration outperforms QVG‑4 by up to 4.95 dB PSNR while reducing cache memory by 37–48 %, and the video‑adapted configuration surpasses QVG‑Pro by 3.77 dB PSNR with 33.7 % less memory, all while maintaining comparable latency and reducing temporal discontinuities.
arXiv:2606. 13035v1 Announce Type: cross Abstract: Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content.
Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift.
arXiv:2610.32784v1 Announce Type: new Abstract: The rapid growth of video data has created an urgent need for efficient video understanding systems that can handle long and continuous visual inputs,...
arXiv:2611.06377v1 Announce Type: new Abstract: Autoregressive video models rely on historical key-value (KV) caches to preserve scene consistency over extended rollouts, making KV storage and repeat...
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.
Focused Forcing is a training‑free method for selecting key‑value (KV) cache entries in autoregressive video diffusion models. It selects historical frames per generated frame by combining attention and diversity scores, and allocates larger budgets to more important heads. The approach yields up to 1.48× faster generation while improving visual quality and text alignment across several generation paradigms.
arXiv:2606. 01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps.
arXiv:2611.05380v1 Announce Type: new Abstract: Visual autoregressive generation spans two dominant paradigms: next-scale prediction for images and video, and next-frame prediction for video. Both de...
arXiv:2609.26425v1 Announce Type: new Abstract: KV cache memory has become a major deployment bottleneck for video generation and world models, which motivates low-bit quantization study for efficien...
arXiv:2608. 08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging.