Related papers: Effect of Human Learning on the Transient Performa…
System responsiveness (SR) is defined as the elapsed time until a system responds to user control. SR fluctuates over time, so it must be described statistically with mean (MSR) and standard deviation (SDSR). In this paper, we examine SR in…
Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…
Bounding the price of anarchy, which quantifies the damage to social welfare due to selfish behavior of the participants, has been an important area of research. In this paper, we study this phenomenon in the context of a game modeling…
Recommender systems play an essential role in music streaming services, prominently in the form of personalized playlists. Exploring the user interactions within these listening sessions can be beneficial to understanding the user…
Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights:…
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data sequentially. CL performance evaluates the model's ability to continually learn and solve new problems with incremental available…
Transient cloud servers such as Amazon Spot instances, Google Preemptible VMs, and Azure Low-priority batch VMs, can reduce cloud computing costs by as much as $10\times$, but can be unilaterally preempted by the cloud provider.…
Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial…
Low latency communication is one of the fundamental requirements for 5G wireless networks and beyond. In this paper, a novel approach for joint caching, user scheduling and resource allocation is proposed for minimizing the queuing latency…
Distributed learning algorithms aim to leverage distributed and diverse data stored at users' devices to learn a global phenomena by performing training amongst participating devices and periodically aggregating their local models'…
Knowledge tracing (KT) aims to leverage students' learning histories to estimate their mastery levels on a set of pre-defined skills, based on which the corresponding future performance can be accurately predicted. As an important way of…
Wearable Cognitive Assistants (WCA) are anticipated to become a widely-used application class, in conjunction with emerging network infrastructures like 5G that incorporate edge computing capabilities. While prototypical studies of such…
Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and…
Programming Knowledge Tracing (PKT) has recently advanced through hybrid approaches that integrate attention-based feature modeling for code representation with RNN-based sequential prediction. While these models report strong empirical…
Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as text to leverage Language Models (LMs) for this task has…
A cloud service provider strives to provide a high Quality of Service (QoS) to client jobs. Such jobs vary in computational and Service-Level-Agreement (SLA) obligations, as well as differ with respect to tolerating delays and SLA…
The rise of Large Language Models (LLMs) has sparked interest in their application to sequential recommendation tasks as they can provide supportive item information. However, due to the inherent complexities of sequential recommendation,…
Cross-application interference can affect drastically performance of HPC applications when running in clouds. This problem is caused by concurrent access performed by co-located applications to shared and non-sliceable resources such as…
Recent advances in test-time scaling suggest that Large Language Models (LLMs) can gain better capabilities by generating Chain-of-Thought reasoning (analogous to human thinking) to respond a given request, and meanwhile exploring more…
The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-the-art online cluster job schedulers use history-based learning, which uses past job execution information to estimate the…