Related papers: PI-JEPA: Label-Free Surrogate Pretraining for Coup…
In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require the…
Mixed-integer optimization is at the core of many online decision-making systems that demand frequent updates of decisions in real time. However, due to their combinatorial nature, mixed-integer linear programs (MILPs) can be difficult to…
Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To…
We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First,…
The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns. Despite considerable progress, the challenge of designing trajectory representations that can capture diverse and…
Operator-based neural network architectures such as DeepONets have emerged as a promising tool for the surrogate modeling of physical systems. In general, towards operator surrogate modeling, the training data is generated by solving the…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or…
There are numerous advantages of deep neural network surrogate modeling for response time-history prediction. However, due to the high cost of refined numerical simulations and actual experiments, the lack of data has become an unavoidable…
Machine learning predictions are increasingly used to supplement incomplete or costly-to-measure outcomes in fields such as biomedical research, environmental science, and social science. However, treating predictions as ground truth…
This article presents an original methodology for the prediction of steady turbulent aerodynamic fields. Due to the important computational cost of high-fidelity aerodynamic simulations, a surrogate model is employed to cope with the…
Accurate characterization of temperature-dependent thermoelectric properties (TEPs), such as thermal conductivity and the Seebeck coefficient, is essential for reliable modeling and efficient design of thermoelectric devices. However, their…
This paper introduces a novel application of Video Joint-Embedding Predictive Architectures (V-JEPAs) for Facial Expression Recognition (FER). Departing from conventional pre-training methods for video understanding that rely on pixel-level…
The success of existing salient object detection models relies on a large pixel-wise labeled training dataset, which is time-consuming and expensive to obtain. We study semi-supervised salient object detection, with access to a small number…
Recent results in end-to-end automatic speech recognition have demonstrated the efficacy of pseudo-labeling for semi-supervised models trained both with Connectionist Temporal Classification (CTC) and Sequence-to-Sequence (seq2seq) losses.…
Autonomous driving, as an agent operating in the physical world, requires the fundamental capability to build \textit{world models} that capture how the environment evolves spatiotemporally in order to support long-term planning. At the…
High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning…
Neural surrogates for partial differential equations (PDEs) have become popular due to their potential to quickly simulate physics. With a few exceptions, neural surrogates generally treat the forward evolution of time-dependent PDEs as a…
This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand…
Recent years have seen a surge in deep learning approaches to accelerate numerical solvers, which provide faithful but computationally intensive simulations of the physical world. These deep surrogates are generally trained in a supervised…