Related papers: Learning in situ: a randomized experiment in video…
Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling. This poses great challenges given the high correlation between…
This paper proposes a novel framework to predict traffic flows' bandwidth ahead of time. Modern network management systems share a common issue: the network situation evolves between the moment the decision is made and the moment when…
Most of the learning-based algorithms for bitrate adaptation are limited to offline learning, which inevitably suffers from the simulation-to-reality gap. Online learning can better adapt to dynamic real-time communication scenes but still…
An influential paper of Hsu et al. (ICLR'19) introduced the study of learning-augmented streaming algorithms in the context of frequency estimation. A fundamental problem in the streaming literature, the goal of frequency estimation is to…
Online experiments in internet systems, also known as A/B tests, are used for a wide range of system tuning problems, such as optimizing recommender system ranking policies and learning adaptive streaming controllers. Decision-makers…
Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is…
We introduce a novel algorithm to perform graph clustering in the edge streaming setting. In this model, the graph is presented as a sequence of edges that can be processed strictly once. Our streaming algorithm has an extremely low memory…
Lifelong learning or continual learning is the problem of training an AI agent continuously while also preventing it from forgetting its previously acquired knowledge. Streaming lifelong learning is a challenging setting of lifelong…
Real-time interactive Virtual Reality (VR) streaming is a significantly challenging use case for Wi-Fi given its high throughput and low latency requirements, especially considering the constraints imposed by the possible presence of other…
Rate control algorithms are at the heart of video conferencing platforms, determining target bitrates that match dynamic network characteristics for high quality. Recent data-driven strategies have shown promise for this challenging task,…
Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed…
Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training…
Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for training models with broad, general capabilities for text, images, and other modalities. However, for many sequential decision domains such as…
Network congestion and packet loss pose an ever-increasing challenge to video streaming. Despite the research efforts toward making video encoding schemes resilient to lossy network conditions, forwarding devices have not considered…
We study streaming algorithms for Correlation Clustering. Given a graph as an arbitrary-order stream of edges, with each edge labeled as positive or negative, the goal is to partition the vertices into disjoint clusters, such that the…
We initiate the study of biological neural networks from the perspective of streaming algorithms. Like computers, human brains suffer from memory limitations which pose a significant obstacle when processing large scale and dynamically…
We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured frame and the actual…
In video streaming over HTTP, the bitrate adaptation selects the quality of video chunks depending on the current network condition. Some previous works have applied deep reinforcement learning (DRL) algorithms to determine the chunk's…
Even real time video telephony services have been pervasively applied, providing satisfactory quality of experience to users is still a challenge task especially in wireless networks. Multipath transmission is a promising solution to…