Related papers: Rapid and Continuous Trust Evaluation for Effectiv…
Trust prediction is a key issue in human-robot collaboration, especially in construction scenarios where maintaining appropriate trust calibration is critical for safety and efficiency. This paper introduces the Performance-guided…
Connected Autonomous Vehicles have great potential to improve automobile safety and traffic flow, especially in cooperative applications where perception data is shared between vehicles. However, this cooperation must be secured from…
Knowledge graph embedding, which aims to learn the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently. However, most knowledge graph embedding methods focus on the structural…
Continuous monitoring of trained ML models to determine when their predictions should and should not be trusted is essential for their safe deployment. Such a framework ought to be high-performing, explainable, post-hoc and actionable. We…
Spiking Neural Networks (SNNs) offer a promising direction for energy-efficient and brain-inspired computing, yet their vulnerability to adversarial perturbations remains poorly understood. In this work, we revisit the adversarial…
When each edge device of a network only perceives a local part of the environment, collaborative inference across multiple devices is often needed to predict global properties of the environment. In safety-critical applications,…
Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential…
The rapid evolution of cyber threats has highlighted significant gaps in security knowledge integration. Cybersecurity Knowledge Graphs (CKGs) relying on structured data inherently exhibit hysteresis, as the timely incorporation of rapidly…
The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low task end-to-end (E2E) latency. However, existing continuous batching methods suffer from…
Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showing a trend of rapid ceiling-hitting by newly developed…
For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various…
In the era of Model-as-a-Service, organizations increasingly rely on third-party AI models for rapid deployment. However, the dynamic nature of emerging AI applications, the continual introduction of new datasets, and the growing number of…
Mobile Crowd-Sensing (MCS) has appeared as a prospective solution for large-scale data collection, leveraging built-in sensors and social applications in mobile devices that enables a variety of Internet of Things (IoT) services. However,…
Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…
There is a great body of work in the areas of tele-assistance/tele-collaboration offering novel and effective ways to improve collaboration between personnel located at a remote mine site and off-site personnel located in major metropolitan…
Social media accounts post increasingly similar content, creating a chaotic experience across platforms, which makes accessing desired information difficult. These posts can be organized by categorizing and grouping duplicates across social…
Split Federated Learning (SFL) offers a promising approach for distributed model training in wireless networks, combining the layer-partitioning advantages of split learning with the federated aggregation that ensures global convergence.…
The rapid advancement of AI technologies and their accelerated adoption in software development necessitates a systematic evaluation of their environmental impact alongside functional correctness. While prior studies have examined…
Historically speaking, it is hard to balance the global and local efficiency of second-order optimization algorithms. For instance, the classical Newton's method possesses excellent local convergence but lacks global guarantees, often…
This paper presents models for detecting agreement/disagreement in online discussions. In this work we show that by using a Siamese inspired architecture to encode the discussions, we no longer need to rely on hand-crafted features to…