Author

Sonia Laguna

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

KV-Kaizen: Learning Context-Adaptive Cache Compression Choices

As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This impacts LLM throughput negatively, since decoding is memory-bound and decode cost grows with cache size. Recent work alleviates this bottleneck by discarding the least re...

João Monteiro, Louis Béthune, A. Filippova et al. · 0 citations

#machine learning Preprint Sep 2026

Cartridges++: KV Cache Compression without Off-Context Derailment

Serving long documents to a Large Language Model (LLM) repeatedly is expensive: computations grow with context length, and the memory footprint of the key-value (KV) cache balloons. Compressed KV (CKV) representations aim to mimic the cache of a document and are typically computed once and for all, ahead of inference t...

Sonia Laguna, João Monteiro, Marco Cuturi et al. · 0 citations