Related papers: PACT: Reducing Alert Fatigue in Low-Prevalence SOC…
The late interaction paradigm introduced with ColBERT stands out in the neural Information Retrieval space, offering a compelling effectiveness-efficiency trade-off across many benchmarks. Efficient late interaction retrieval is based on an…
Error detection in relational databases is critical for maintaining data quality and is fundamental to tasks such as data cleaning and assessment. Current error detection studies mostly employ the multi-detector approach to handle…
Target tracking is a popular problem with many potential applications. There has been a lot of effort on improving the quality of the detection of targets using cameras through different techniques. In general, with higher computational…
Federated learning (FL) is attractive for cloud-edge intrusion detection because it enables collaborative training over distributed telemetry without centralizing raw logs. In production security analytics pipelines, however, only a subset…
Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an…
Contact-implicit trajectory optimization (CITO) has attracted growing attention as a unified framework for planning and control in contact-rich robotic tasks. Recent approaches have demonstrated promising results in manipulation and…
Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial…
Static Application Security Testing (SAST) tools play a vital role in modern software development by automatically detecting potential vulnerabilities in source code. However, their effectiveness is often limited by a high rate of false…
Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is…
Parent-Guided Adaptive Reliability (PGAR) is a lightweight behavioural meta-learning framework that adds a supervisory "parent" layer on top of a standard learner to improve stability, calibration, and recovery under disturbances. PGAR…
This paper addresses the problem of output consensus in linear passive multi-agent systems under a False Data Injection (FDI) attack, considering the unavailability of complete state information. Our formulation relies on an event-based…
Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods…
Enterprise environments contain a heterogeneous, rapidly growing collection of internal artifacts related to code, data, and many different tools. Critical information for assessing privacy risk and ensuring regulatory compliance is often…
Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…
Federated learning (FL) emerged as a popular distributed algorithm to train machine learning models on edge devices while preserving data privacy. However, FL systems face challenges due to client-side computational constraints and from a…
Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on…
Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertainty-, or difficulty-based gates, assuming a fixed direction from the gating…
Prompt design is a critical factor in the effectiveness of Large Language Models (LLMs), yet remains largely heuristic, manual, and difficult to scale. This paper presents the first comprehensive evaluation of Automatic Prompt Optimization…
Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary…
We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our…