Showing 2025Show all
3 papers · 1 filter
cs.CV2025
RANa: Retrieval-Augmented Navigation
Gianluca Monaci, Rafael S. Rezende, Romain Deffayet +5
Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While…
cs.IR2025
Reranking with Compressed Document Representation
Hervé Déjean, Stéphane Clinchant
Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recen…
cs.CL2025
PISCO: Pretty Simple Compression for Retrieval-Augmented Generation
Maxime Louis, Hervé Déjean, Stéphane Clinchant
Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs a…