Author

Alessandro De Bellis

h-index 2 View on Semantic Scholar

We have 1 of 3 papers

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.

Preprint Aug 2026

PUMA: Post-Hoc Sparsification of Universal Multimodal Embeddings for Efficient Retrieval

PUMA, a sparse autoencoder recipe that maps universal multimodal embeddings to compact sparse codes without retraining the backbone, reduces vector storage by 8-16x (FP32) and is up to 25x faster than exact dense scoring on larger candidate pools, enabling efficient multimodal retrieval.

Matteo Attimonelli, Alessandro De Bellis, Franco Maria Nardini et al. · 0 citations