Publications by authors named "A Carballo"
Integrating multiple types of sensors into autonomous systems, such as cars and robots, has become a widely adopted approach in modern technology. Among these sensors, RGB cameras, thermal cameras, and LiDAR are particularly valued for their ability to provide comprehensive environmental data. However, despite their advantages, current research primarily focuses on the one or combination of two sensors at a time.
View Article and Find Full Text PDFArticle Synopsis
- The paper introduces MulCPred, a new framework designed to provide explainable predictions for pedestrian action, which is essential for applications like autonomous driving.
- It addresses limitations of existing methods by using a linear aggregator for multi-modal concept integration, a channel-wise recalibration module for focusing on detailed input areas, and a regularization loss to capture diverse patterns.
- Evaluation on various datasets shows that MulCPred enhances the explainability of predictions without significantly harming accuracy, and by filtering out unrecognizable concepts, it improves performance across different datasets.
Article Synopsis
- The Letter reports the most accurate measurement so far of the matter-antimatter imbalance during Pb-Pb collisions at a high energy level of 5.02 TeV.
- It utilizes the Statistical Hadronization framework to determine precise values for the electric charge and baryon chemical potentials, μ_{Q} and μ_{B}.
- The analysis of antiparticle-to-particle yield ratios shows that the collisions create a system that is generally baryon-free and electrically neutral at midrapidity.
The ALICE Collaboration reports the measurement of semi-inclusive distributions of charged-particle jets recoiling from a high transverse momentum (high p_{T}) hadron trigger in proton-proton and central Pb-Pb collisions at sqrt[s_{NN}]=5.02 TeV. A data-driven statistical method is used to mitigate the large uncorrelated background in central Pb-Pb collisions.
View Article and Find Full Text PDFCognitive scientists believe that adaptable intelligent agents like humans perform spatial reasoning tasks by learned causal mental simulation. The problem of learning these simulations is called predictive world modeling. We present the first framework for a learning open-vocabulary predictive world model (OV-PWM) from sensor observations.
View Article and Find Full Text PDF