arXiv Computer Vision
VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 23
QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generation
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 Machine Learning
Oct 12
CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches
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 Computer Vision
Oct 26
Video-MemComp: Taylor-Guided Sensitivity-Aware Memory Management for Streaming Video Understanding
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 Machine Learning
Oct 15
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
arXiv:2605.19660v3 Announce Type: replace Abstract: The rapid advancement toward long-context reasoning and multi-modal intelligence has made the memory footprint of the Key-Value (KV) cache a domina...
arXiv Computer Vision
1d ago
NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation
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 Machine Learning
Jul 9
Activation Quantization of Vision Encoders Needs Prefixing Registers
arXiv:2510. 04547v5 Announce Type: replace Abstract: Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models.