This work learns a selector that is able to produce, based on context, a per-layer cache configuration towards an overall compression budget, and achieves the Pareto frontier of accuracy against cache size, against learning-free and post-hoc baselines.
João Monteiro, Louis Béthune, A. Filippova et al.· arXiv.org· 1 citation
DynaMiCS is proposed, a dynamic mixture optimizer that casts multi-domain fine-tuning as a constrained optimization problem, and achieves stronger target-domain improvements and higher constraint satisfaction than static, dynamic, similarity-based and probing-based alternatives, without a reference model, per-example s...
Eleonora Gualdoni, Sonia Laguna, Louis Béthune et al.· arXiv.org· 2 citations· ⚡1
This study investigates the crucial deployment question of whether Cartridges and other CKVs can handle off-context queries, and proposes Cartridges++, simple modifications to cartridges that retain off-context abilities at small or negligible cost.
Sonia Laguna, João Monteiro, Marco Cuturi et al.· arXiv.org· 1 citation
ConRAG is introduced, which builds a lightweight entity-document graph from entity co-occurrence and LLM-based entity filtering that consistently improves bridge entity and reasoning chain recovery over strong RAG baselines, while reducing graph-indexing token cost by up to roughly 1.5 orders of magnitude.
Kilian Bänziger, Sonia Laguna, Markus Kreft et al.· 0 citations
Across modalities, the results show that explicitly encoding measurable cyclic structure improves physiological time-series restoration and proposes antithetic coupling of reverse trajectories to reduce sampling variance while achieving comparable performance with fivefold fewer network evaluations.
Samuel Ruipérez-Campillo, Michele Copetti, Jorge da Silva Goncalves et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.