Related papers: ODEStream: A Buffer-Free Online Learning Framework…

A streaming algorithm is adversarially robust if it is guaranteed to perform correctly even in the presence of an adaptive adversary. Recently, several sophisticated frameworks for robustification of classical streaming algorithms have been…

We consider the problem of online learning in the presence of distribution shifts that occur at an unknown rate and of unknown intensity. We derive a new Bayesian online inference approach to simultaneously infer these distribution shifts…

Anomaly detection is critical for finding suspicious behavior in innumerable systems. We need to detect anomalies in real-time, i.e. determine if an incoming entity is anomalous or not, as soon as we receive it, to minimize the effects of…

We study the well-motivated problem of online distribution shift in which the data arrive in batches and the distribution of each batch can change arbitrarily over time. Since the shifts can be large or small, abrupt or gradual, the length…

Inferring the evolution of high-dimensional and multi-modal (e.g., spatio-temporal) physical fields from irregular sparse measurements in real time is a fundamental challenge in science and engineering. Existing approaches, including…

Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory…

This paper presents a framework for the analysis of changes in visual streams: ordered sequences of images, possibly separated by significant time gaps. We propose a new approach to incorporating unlabeled data into training to generate…

With the increasing volume of streaming data in industrial systems, online anomaly detection has become a critical task. The diverse and rapidly evolving data patterns pose significant challenges for online anomaly detection. Many existing…

The detection of anomalies in non-stationary time-series streams is a critical but challenging task across numerous industrial and scientific domains. Traditional models, trained offline, suffer significant performance degradation when…

This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve…

The use of time series for sequential online prediction (SOP) has long been a research topic, but achieving robust and computationally efficient SOP with non-stationary time series remains a challenge. This paper reviews a framework, called…

Real-time video analytics systems typically place models with fewer weights on edge devices to reduce latency. The distribution of video content features may change over time for various reasons (i.e. light and weather change) , leading to…

Operations over data streams typically hinge on efficient mechanisms to aggregate or summarize history on a rolling basis. For high-volume data steams, it is critical to manage state in a manner that is fast and memory efficient --…

With the rapid growth of traffic sensors deployed, a massive amount of traffic flow data are collected, revealing the long-term evolution of traffic flows and the gradual expansion of traffic networks. How to accurately forecasting these…

Non-stationarity poses significant challenges for multivariate time series forecasting due to the inherent short-term fluctuations and long-term trends that can lead to spurious regressions or obscure essential long-term relationships. Most…

Data streams in real-world industrial scenarios often contain transitional operating conditions that are uncovered during offline training, leading to significant distribution shifts. To bridge the gap between static offline models and…

Imagine a smart camera trap selectively clicking pictures to understand animal movement patterns within a particular habitat. These "snapshots", or pieces of data captured from a data stream at adaptively chosen times, provide a glimpse of…

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables…

In recent years, deep neural networks have shown remarkable progress in dense disparity estimation from dynamic scenes in monocular structured light systems. However, their performance significantly drops when applied in unseen…

Trajectory forecasting is a widely-studied problem for autonomous navigation. However, existing benchmarks evaluate forecasting based on independent snapshots of trajectories, which are not representative of real-world applications that…