uncertainty quantification
PulseAugur coverage of uncertainty quantification — every cluster mentioning uncertainty quantification across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New framework uses Hill numbers to quantify LLM uncertainty in social sciences
A new research paper proposes a framework for evaluating uncertainty in Large Language Models (LLMs) when applied to social science research. The paper argues that explicit assessment of uncertainty is crucial for scien…
-
Review explores uncertainty quantification for machine learning in biosignal analysis
A recent review paper explores the application of Uncertainty Quantification (UQ) in machine learning models designed for biosignal analysis. The research highlights UQ's potential to enhance the interpretability and ro…
-
Deep Reinforcement Learning Framework Tackles Distribution Network Risks
Researchers have developed a deep reinforcement learning framework to identify operational risks and anomalies in distribution networks, particularly under conditions of uncertainty. The proposed method integrates distr…
-
AdaptNTK framework enhances AI for molecular dynamics simulations
Researchers have developed AdaptNTK, a novel framework for quantifying uncertainty and implementing active learning in neural network potentials. This single-model approach uses a regularized Mahalanobis distance in emp…
-
Conformal Prediction and DRO Unified for Uncertainty Quantification
Researchers have developed a unified probabilistic framework that connects conformal prediction (CP) and distributionally robust optimization (DRO) for uncertainty quantification. This new perspective views both methods…
-
Supervised ensembles boost LLM hallucination detection
Researchers have investigated the effectiveness of supervised ensembles for detecting hallucinations in large language models (LLMs). Their study, conducted across four LLMs, nine datasets, and three generation regimes,…
-
New method integrates aleatoric and epistemic uncertainty in deep learning
Researchers have developed a new method for uncertainty quantification (UQ) in deep learning models, particularly for high-dimensional output spaces. This approach jointly models aleatoric uncertainty, which accounts fo…
-
LLM agents face 'sim-to-real' gap, mirroring RL challenges, says ASU professor
Hua Wei, an assistant professor at Arizona State University, argues that the current challenges faced by large language model (LLM) agents in real-world applications mirror the "sim-to-real" gap encountered in tradition…
-
New research explores uncertainty quantification and lightweight models for semantic segmentation
Researchers are exploring methods to improve the reliability and robustness of semantic segmentation models, particularly for safety-critical applications. One paper investigates the integration of uncertainty quantific…
-
AI framework enhances drug discovery with reliable molecular property predictions
Researchers have developed a new conformal prediction framework designed to improve the reliability of AI in drug discovery, particularly when dealing with label shift. This method generates statistically rigorous predi…
-
New framework enhances neural network reconstruction of random fields
Researchers have introduced a new local Sinkhorn divergence framework designed for training stochastic neural networks (SNNs) to reconstruct multidimensional random fields. This framework utilizes debiased Sinkhorn dive…
-
New CRUISE framework enhances autonomous driving sensor fusion with VLM-guided uncertainty
Researchers have developed CRUISE, a new framework for autonomous driving that enhances sensor fusion by incorporating uncertainty quantification guided by a vision-language model (VLM). This approach aims to improve th…
-
Structured Neural Chaos framework enhances uncertainty quantification
Researchers have introduced Structured Neural Chaos (sNC), a novel surrogate modeling framework designed for uncertainty quantification and global sensitivity analysis. This approach combines the interpretability of pol…
-
New survey details uncertainty quantification for trustworthy deep learning
A new survey paper published on arXiv details methods for uncertainty quantification in deep learning, focusing on techniques relevant for trustworthy AI in safety-critical applications. The paper categorizes approaches…
-
AI Uncertainty Quantification: Taxonomy, Validation, and Trustworthiness
A new paper on arXiv, "Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation," by Ramon Winterhalder and others, provides a structured overview of uncertainty quantification in machine learning for phy…
-
Bayesian probability theory offers unified framework for mechanics uncertainty quantification
A new paper proposes a unified Bayesian probability theory framework for uncertainty quantification (UQ) in mechanics. This approach addresses both forward problems, which track how input uncertainties affect outcomes, …
-
New UQ Framework Derives Uncertainty Measures from Subjective Risk Decomposition
Researchers have introduced a new perspective on uncertainty quantification (UQ) by proposing that uncertainty measures are not fundamental but rather derived from higher-level modeling decisions. This framework shows h…
-
New research highlights CoT inefficiency and overconfidence in LLMs and VLMs
Researchers have identified inefficiencies in Chain-of-Thought (CoT) prompting for large language models (LLMs), where valid but redundant reasoning steps increase computational costs without improving accuracy. A new d…
-
New deep learning model classifies astronomical transients without human labels
Researchers have developed a novel deep learning framework for classifying astronomical transients as real or bogus without requiring human-labeled data. This method utilizes injected simulated transients and a contamin…
-
New von Mises ensemble improves uncertainty quantification for automotive radar
Researchers have developed a new uncertainty quantification method for automotive radar systems using a von Mises (VM) ensemble, which offers improved interpretability and geometric consistency compared to evidential de…