Related papers: The Effects of Latency Penalties in Evaluating Pus…
Text summarization aims at compressing long documents into a shorter form that conveys the most important parts of the original document. Despite increased interest in the community and notable research effort, progress on benchmark…
Modern public blockchains like Ethereum rely on p2p networks to run distributed and censorship-resistant applications. With its wide adoption, it operates as a highly critical public ledger. On its transition to become more scalable and…
Closed-loop or feedback control ratchets use information about the state of the system to operate with the aim of maximizing the performance of the system. In this paper we investigate the effects of a time delay in the feedback for a…
There are many algorithms for regret minimisation in episodic reinforcement learning. This problem is well-understood from a theoretical perspective, providing that the sequences of states, actions and rewards associated with each episode…
Context: Contemporary code review tools are a popular choice for software quality assurance. Using these tools, reviewers are able to post a linkage between two patches during a review discussion. Large development teams that use a…
Existing models of Multi-Hop Wireless Networks (MHWNs) assume that interference estimators of link quality such as observed busy time predict the capacity of the links. We show that these estimators do not capture the intricate interactions…
Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples. This flexibility suits real deployments, yet…
Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary annotations. Weakly supervised methods with cheaper…
As machine learning models become increasingly prevalent in time series applications, Explainable Artificial Intelligence (XAI) methods are essential for understanding their predictions. Within XAI, feature attribution methods aim to…
Multi-threaded applications are capable of exploiting the full potential of many-core systems. However, Network-on-Chip (NoC) based inter-core communication in many-core systems is responsible for 60-75% of the miss latency experienced by…
Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We…
Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…
Changes in parameters of a physical device can eventually lead to catastrophic failure. This paper discusses a parameter estimation method based on synchronization between a model and time series data. In particular, we examine the…
When an NLP model is trained on text data from one time period and tested or deployed on data from another, the resulting temporal misalignment can degrade end-task performance. In this work, we establish a suite of eight diverse tasks…
Grades provide students with their primary performance feedback: signals which affect academic choices. Variations in grading practice among courses impose grade penalties (and bonuses) on students who take them. These grade penalties are…
The Logical Execution Time (LET) model has deterministic properties which dramatically reduce the complexity of analyzing temporal requirements of multi-rate cause-effect chains. The configuration (length and position) of task's…
We study the effects of nonzero time delays in stochastic synchronization problems with linear couplings in complex networks. We consider two types of time delays: transmission delays between interacting nodes and local delays at each node…
Building systems that are good for society in the face of complex societal effects requires a dynamic approach. Recent approaches to machine learning (ML) documentation have demonstrated the promise of discursive frameworks for deliberation…
Users of music streaming, video streaming, news recommendation, and e-commerce services often engage with content in a sequential manner. Providing and evaluating good sequences of recommendations is therefore a central problem for these…
Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limiting reuse of…