Related papers: TCUQ: Single-Pass Uncertainty Quantification from …
As large language models are increasingly deployed for clinical text, ensuring they can reliably signal their own uncertainty becomes critical. Most existing uncertainty quantification (UQ) methods are designed for open-domain generation…
Large language models (LLMs) are increasingly utilized for machine translation, yet their predictions often exhibit uncertainties that hinder interpretability and user trust. Effectively visualizing these uncertainties can enhance the…
Uncertainty quantification (UQ) has emerged as a promising approach for detecting hallucinations and low-quality output of Large Language Models (LLMs). However, obtaining proper uncertainty scores is complicated by the conditional…
We present MaestroCut, a closed-loop framework for quantum circuit cutting that adapts partitioning and shot allocation to device drift and workload variation. MaestroCut tracks a variance proxy in real time, triggers re-cutting when…
In this paper, we propose and analyze a new method for online linear quadratic regulator (LQR) control with a priori unknown time-varying cost matrices. The cost matrices are revealed sequentially with the potential for future values to be…
In place of in-house solutions, organizations are increasingly moving towards managed services for cyber defense. Security Operations Centers are specialized cybersecurity units responsible for the defense of an organization, but the…
There is a need to build intelligence in operating machinery and use data analysis on monitored signals in order to quantify the health of the operating system and self-diagnose any initiations of fault. Built-in control procedures can…
Android malware detection continues to face persistent challenges stemming from long-term concept drift and class imbalance, as evolving malicious behaviors and shifting usage patterns dynamically reshape feature distributions. Although…
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is…
We present an optimal uncertainty quantification (OUQ) framework for systems whose uncertain inputs are characterized by truncated moment constraints defined over subdomains. Based on this partial information, rigorous optimal upper and…
Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…
In this paper, we present a lightweight and effective change detection model, called TinyCD. This model has been designed to be faster and smaller than current state-of-the-art change detection models due to industrial needs. Despite being…
TinyML models often operate in remote, dynamic environments without cloud connectivity, making them prone to failures. Ensuring reliability in such scenarios requires not only detecting model failures but also identifying their root causes.…
Most methods for learning with noisy labels require privileged knowledge such as noise transition matrices, clean subsets or pretrained feature extractors, resources typically unavailable when robustness is most needed. We propose Conformal…
As the Internet of Things (IoT) becomes an integral part of critical infrastructure and commercial services, runtime firmware attestation of constituent Micro-Controllers (MCUs) has become instrumental in maintaining security and trust.…
While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty…
Future 5G systems will need to support ultra-reliable low-latency communications scenarios. From a latency-reliability viewpoint, it is inefficient to rely on average utility-based system design. Therefore, we introduce the notion of…
In this paper, we propose trellis coded quantization (TCQ) based limited feedback techniques for massive multiple-input single-output (MISO) frequency division duplexing (FDD) systems in temporally and spatially correlated channels. We…
Recognizing and localizing student confusion from video is an important yet challenging problem in educational AI. Existing confusion datasets suffer from noisy labels, coarse temporal annotations, and limited expert validation, which…
Token-based replay used to be the standard way to conduct conformance checking. With the uptake of more advanced techniques (e.g., alignment based), token-based replay got abandoned. However, despite decomposition approaches and heuristics…