KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity
Published in AISTATS 2026, 2025
Recommended citation: Lesens, D., Rakhshan, B. T., Rabusseau, G. KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity. In The 29th International Conference on Artificial Intelligence and Statistics.
Download Paper | Download Slides
