Related papers: Event Fields: Learning Latent Event Structure for …

Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a generative perspective…

Event cameras are bio-inspired sensors that capture intensity changes asynchronously with distinct advantages, such as high temporal resolution. Existing methods for event-based object/action recognition predominantly sample and convert…

Time series classification (TSC) of biological signals has progressed from handcrafted, modality-specific approaches to deep architectures capable of representing the diverse waveform structures of underlying physiological processes (i.e.,…

World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are often either learned directly from pixels with limited…

Event vision sensors (neuromorphic cameras) output sparse, asynchronous ON/OFF events triggered by log-intensity threshold crossings, enabling microsecond-scale sensing with high dynamic range and low data bandwidth. As a nonlinear system,…

The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying quantities such as heterogeneous material properties and turbulent flows. Deep generative…

Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex…

Despite the significant recent progress in deep generative models, the underlying structure of their latent spaces is still poorly understood, thereby making the task of performing semantically meaningful latent traversals an open research…

We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels. This powerful weakly-supervised framework alleviates the burden of…

Electroencephalography (EEG) reflects the brain's functional state, making it a crucial tool for diverse detection applications like seizure detection and sleep stage classification. While deep learning-based approaches have recently shown…

Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the…

In science, we are interested not only in forecasting but also in understanding how predictions are made, specifically what the interpretable underlying model looks like. Data-driven machine learning technology can significantly streamline…

In this paper, we describe the use of recurrent neural networks to capture sequential information from the self-attention representations to improve the Transformers. Although self-attention mechanism provides a means to exploit long…

We introduce a new class of latent process models for dynamic relational network data with the goal of detecting time-dependent structure. Network data are often observed over time, and static network models for such data may fail to…

This paper presents a machine learning method for event cause analysis to enhance situational awareness in distribution networks. The data streams are captured using time-synchronized high sampling rates synchro waveform measurement units…

Context, as referred to situational factors related to the object of interest, can help infer the object's states or properties in visual recognition. As such contextual features are too diverse (across instances) to be annotated, existing…

Normalizing flow (NF) has gained popularity over traditional maximum likelihood based methods due to its strong capability to model complex data distributions. However, the standard approach, which maps the observed data to a normal…

Video diffusion models have achieved impressive results in natural scene generation, yet they struggle to generalize to scientific phenomena such as fluid simulations and meteorological processes, where underlying dynamics are governed by…

Persistent homology is a cornerstone of topological data analysis, offering a multiscale summary of topology with robustness to nuisance transformations, such as rotations and small deformations. Persistent homology has seen broad use…

Models of narrative schema knowledge have proven useful for a range of event-related tasks, but they typically do not capture the temporal relationships between events. We propose a single model that addresses both temporal ordering,…