[EN] Pretrained artificial intelligence models are made more human-like and human-aligned by scaling them up in resources (e.g., by increasing compute, training data and parameter size) and shaping them up with human feedback. One of the major concerns about the trustworthiness of Large Language Models (LLMs) is their unpredictability from the human point of view. First, the model can solve very challenging tasks while some questions that are considered easy by humans are completely missed by these models (difficulty discordance). Second, models that avoid answering the questions and digress in an unpredictable way may also be considered unreliable (task avoidance). Third, the same question can get solved or not depending on minor changes i...
Successful interaction with environment would seem to require human agents to possess insight about ...
La cerca d’objectes de text en imatges d’escena reals és un problema obert i una àrea de cerca molt...
[EN] This thesis considers new applications of non-Gaussian mixtures in the framework of statistical...
[EN] Pretrained artificial intelligence models are made more human-like and human-aligned by scaling...
[eng] The representation (or feature) learning has been an emerging concept in the last years, sinc...
This dissertation formalizes the construction of multi-view 2D shape models from 3D data. We propose...
El aprendizaje automático es una disciplina dentro del ámbito de la inteligencia artificial que impl...
[ES] Los sistemas naturales de agua dulce se ven ampliamente afectados por las presiones hidromorfol...
L'objectiu general d'aquest treball és posar de relleu alguns problemes relacionats amb la teoria de...
Dia a dia, la capacitat de detectar i reconèixer objectes en imatges automàticament es fa cada vegad...
Mención Internacional en el título de doctorAggregated data commonly appear in areas such as epidemi...
Air pollution is an important topic with a great social impact; it is related with public health, en...
Visual analysis of human movements concerns the understanding of human activities from image sequenc...
Collective variables (CVs) are low-dimensional representations of the state of a complex system, whi...
Esta tesis contribuye a la caracterización del movimiento a través de señales inerciales y fisiológi...
Successful interaction with environment would seem to require human agents to possess insight about ...
La cerca d’objectes de text en imatges d’escena reals és un problema obert i una àrea de cerca molt...
[EN] This thesis considers new applications of non-Gaussian mixtures in the framework of statistical...
[EN] Pretrained artificial intelligence models are made more human-like and human-aligned by scaling...
[eng] The representation (or feature) learning has been an emerging concept in the last years, sinc...
This dissertation formalizes the construction of multi-view 2D shape models from 3D data. We propose...
El aprendizaje automático es una disciplina dentro del ámbito de la inteligencia artificial que impl...
[ES] Los sistemas naturales de agua dulce se ven ampliamente afectados por las presiones hidromorfol...
L'objectiu general d'aquest treball és posar de relleu alguns problemes relacionats amb la teoria de...
Dia a dia, la capacitat de detectar i reconèixer objectes en imatges automàticament es fa cada vegad...
Mención Internacional en el título de doctorAggregated data commonly appear in areas such as epidemi...
Air pollution is an important topic with a great social impact; it is related with public health, en...
Visual analysis of human movements concerns the understanding of human activities from image sequenc...
Collective variables (CVs) are low-dimensional representations of the state of a complex system, whi...
Esta tesis contribuye a la caracterización del movimiento a través de señales inerciales y fisiológi...
Successful interaction with environment would seem to require human agents to possess insight about ...
La cerca d’objectes de text en imatges d’escena reals és un problema obert i una àrea de cerca molt...
[EN] This thesis considers new applications of non-Gaussian mixtures in the framework of statistical...