Related papers: FoMEMO: Towards Foundation Models for Expensive Mu…
Foundation models (FMs) are a popular topic of research in AI. Their ability to generalize to new tasks and datasets without retraining or needing an abundance of data makes them an appealing candidate for applications on specialist…
Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent motion benchmarks, primarily due to the scarcity of…
Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to…
Multi-objective optimization aims at finding trade-off solutions to conflicting objectives. These constitute the Pareto optimal set. In the context of expensive-to-evaluate functions, it is impossible and often non-informative to look for…
Multi-task dense prediction, which aims to jointly solve tasks like semantic segmentation and depth estimation, is crucial for robotics applications but suffers from domain shift when deploying models in new environments. While unsupervised…
As evolutionary algorithms (EAs) are general-purpose optimization algorithms, recent theoretical studies have tried to analyze their performance for solving general problem classes, with the goal of providing a general theoretical…
Data-driven modeling of constrained multibody dynamics remains challenged by (i) the training cost of Neural ODEs, which typically require backpropagation through an ODE solver, and (ii) error accumulation in rollout predictions. We…
Automated experimentation has the potential to revolutionize scientific discovery, but its effectiveness depends on well-defined optimization targets, which are often uncertain or probabilistic in real-world settings. In this work, we…
Federated edge learning (FEEL) has recently emerged as a promising paradigm for achieving edge intelligence (EI) via enabling collaborative model training across edge devices while protecting data privacy. In this paper, we put forth an…
Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size. These models achieve state-of-the-art performance (often through further adaptation) on a…
Multi-objective optimization is now a core paradigm in engineering design and scientific discovery. Yet mainstream evolutionary frameworks, including \textit{pymoo}, still depend on imperative coding for problem definition, algorithm…
Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have recently addressed handling continual data streams. However,…
Many real-world applications involve black-box optimization of multiple objectives using continuous function approximations that trade-off accuracy and resource cost of evaluation. For example, in rocket launching research, we need to find…
One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL). However, in practice, applying gradient descent (GD) on the average loss across all…
Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimization and multiobjective optimal control is therefore to…
The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the…
Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is…
Imitation learning has unlocked the potential for robots to exhibit highly dexterous behaviours. However, it still struggles with long-horizon, multi-object tasks due to poor sample efficiency and limited generalisation. Existing methods…
We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast volumes of data spanning diverse physical regimes and scales. Training foundation models…
Some real problems require the evaluation of expensive and noisy objective functions. Moreover, the analytical expression of these objective functions may be unknown. These functions are known as black-boxes, for example, estimating the…