4 papers
Influence Functions for Efficient Data Selection in Reasoning
Prateek Humane, Paolo Cudrano, Daniel Z. Kaplan +3
Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quali…
The Empirical Impact of Forgetting and Transfer in Continual Visual Odometry
Paolo Cudrano, Xiaoyu Luo, Matteo Matteucci
As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability an…
Can Shape-Infused Joint Embeddings Improve Image-Conditioned 3D Diffusion?
Cristian Sbrolli, Paolo Cudrano, Matteo Matteucci
Recent advancements in deep generative models, particularly with the application of CLIP (Contrastive Language Image Pretraining) to Denoising Diffusion Probabilistic Models (DDPMs…
RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline
Mirko Usuelli, Matteo Frosi, Paolo Cudrano +2
Loop Closure Detection (LCD) is an essential task in robotics and computer vision, serving as a fundamental component for various applications across diverse domains. These applica…