Related papers: OTAS: An Elastic Transformer Serving System via To…
Variable count is among the main scalability bottlenecks for transformer modeling in multivariate time series (MTS) data. On top of this, a growing consensus in the field points to indiscriminate inter-variable mixing as a potential source…
As the AI community increasingly adopts large-scale models, it is crucial to develop general and flexible tools to integrate them. We introduce Gather-Attend-Scatter (GATS), a novel module that enables seamless combination of pretrained…
Metadata hotspots remain one of the key obstacles to scalable Input/Output (I/O) in both High-Performance Computing (HPC) and cloud-scale storage environments. Situations such as job start-ups, checkpoint storms, or heavily skewed namespace…
Over-the-air (OTA) computation has emerged as a promising technique for efficiently aggregating data from massive numbers of wireless devices. OTA computations can be performed by analog or digital communications. Analog OTA systems are…
This paper introduces SLOs-Serve, a system designed for serving multi-stage large language model (LLM) requests with application- and stage-specific service level objectives (SLOs). The key idea behind SLOs-Serve is to customize the…
While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…
Satellite-terrestrial networks (STNs) are anticipated to deliver seamless IoT services across expansive regions. Given the constrained resources available for offloading computationally intensive tasks like video streaming, it is crucial to…
Autoregressive policies offer a compelling foundation for scalable robot learning by enabling discrete abstraction, token-level reasoning, and flexible inference. However, applying autoregressive modeling to continuous robot actions…
Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…
Deep learning is experiencing a rise in large-scale models. Training large-scale models is costly, prompting researchers to train large-scale models on commodity servers that more researchers can access. The massive number of parameters…
Performance tuning of Database Management Systems(DBMS) is both complex and challenging as it involves identifying and altering several key performance tuning parameters. The quality of tuning and the extent of performance enhancement…
Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching…
Efficient load balancing is crucial in cloud computing environments to ensure optimal resource utilization, minimize response times, and prevent server overload. Traditional load balancing algorithms, such as round-robin or least…
In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can…
Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length. General efficient transformers are…
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few…
Cloud data centers are evolving fast. At the same time, today's large-scale data analytics applications require non-trivial performance tuning that is often specific to the applications, workloads, and data center infrastructure. We propose…
Learning performant robot manipulation policies can be challenging due to high-dimensional continuous actions and complex physics-based dynamics. This can be alleviated through intelligent choice of action space. Operational Space Control…
Serverless architectures, particularly the Function as a Service (FaaS) model, have become a cornerstone of modern cloud computing due to their ability to simplify resource management and enhance application deployment agility. However, a…
We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). The goal is to control a nonlinear system subject to adversarial disturbance and unknown…