Related papers: Railgun: managing large streaming windows under MA…
Streaming data applications are becoming more common due to the ability of different information sources to continuously capture or produce data, such as sensors and social media. Despite recent advances, most visualization approaches, in…
We present Rhino, a system for accelerating tensor programs with automatic parallelization on AI platform for real production environment. It transforms a tensor program written for a single device into an equivalent distributed program…
Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs)…
Most popular, modern network simulators, such as ns, are targeted towards simulating low-level protocol details. These existing simulators are not intended for simulating large distributed applications with many hosts and many concurrent…
Executing distributed cyber-physical software processes on edge devices that maintains the resiliency of the overall system while adhering to resource constraints is quite a challenging trade-off to consider for developers. Current…
Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models. This incompatibility precludes reusing robust AR priors,…
3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands relatively significant GPU memory, limiting its use on…
Information diffusion in social networks facilitates rapid and large-scale propagation of content. However, spontaneous diffusion behavior could also lead to the cascading of sensitive information, which is neglected in prior arts. In this…
We investigate the problem of minimizing the expectation of smooth nonconvex functions in a distributed setting with multiple parallel workers that are able to compute stochastic gradients. A significant challenge in this context is the…
The pervasive availability of streaming data is driving interest in distributed Fast Data platforms for streaming applications. Such latency-sensitive applications need to respond to dynamism in the input rates and task behavior using…
There is an emerging trend in applying deep learning methods to control complex nonlinear systems. This paper considers enhancing the runtime safety of nonlinear systems controlled by neural networks in the presence of disturbance and…
High throughput and low latency data processing is essential for systems requiring live decision making, control, and machine learning-optimized data reduction. We focus on two distinct use cases for in-flight streaming data processing for…
Understanding and tuning the performance of extreme-scale parallel computing systems demands a streaming approach due to the computational cost of applying offline algorithms to vast amounts of performance log data. Analyzing large…
Distributed stream processing systems are widely deployed to process real-time data generated by various devices, such as sensors and software systems. A key challenge in the system is overloading, which leads to an unstable system status…
Machine learning systems deployed in safety-critical robotics settings must be robust to distribution shifts. However, system designers must understand the cause of a distribution shift in order to implement the appropriate intervention or…
This paper introduces a scheme for data stream processing which is robust to batch duration. Streaming frameworks process streams in batches retrieved at fixed time intervals. In a common setting a pattern recognition algorithm is applied…
Real time large scale streaming data pose major challenges to forecasting, in particular defying the presence of human experts to perform the corresponding analysis. We present here a class of models and methods used to develop an…
Motivated by emerging vision-based intelligent services, we consider the problem of rate adaptation for high quality and low delay visual information delivery over wireless networks using scalable video coding. Rate adaptation in this…
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.…
High-fidelity physics simulation is essential for closing the sim-to-real gap in robotics and complex mechanical systems. However, the computational overhead of high-fidelity engines often limits their use in data-intensive tasks like…