🧪 Test?View on arXiv
CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches
Not provided in the abstract
video generationcache optimizationautoregressive models
2610.12514
Builder Relevance
8h ago80%
Abstract
Coral-KV is a KV-cache compression framework that improves memory efficiency and video generation fidelity by predicting keys and values across cache layers.
Reality Card
Core Claim
Coral-KV improves PSNR by up to 4.95 dB while reducing cache memory usage by up to 48% compared to existing methods.
Method / Result
Improved PSNR by 4.95 dB while using 37% less cache memory on MAGI-1.
Limitations
The paper does not provide specific details on the implementation or datasets used for reproducibility.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.