3 papers
cs.LG2026
Dynamic Tool Dependency Retrieval for Lightweight Function Calling
Bhrij Patel, Davide Belli, Amir Jalalirad +3
Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevan…
cs.LG2025
Neural Augmented Kalman Filters for Road Network assisted GNSS positioning
Hans van Gorp, Davide Belli, Amir Jalalirad +1
The Global Navigation Satellite System (GNSS) provides critical positioning information globally, but its accuracy in dense urban environments is often compromised by multipath and…
cs.LG2025
Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking
Marco Federici, Davide Belli, Mart van Baalen +5
While mobile devices provide ever more compute power, improvements in DRAM bandwidth are much slower. This is unfortunate for large language model (LLM) token generation, which is…