Tag
EnergyMamba proposes a novel spatiotemporal framework combining a graph-enhanced selective state space model and adaptive conformalized quantile regression for accurate and reliable energy consumption prediction with uncertainty estimates, achieving improvements on real-world datasets from Florida, New York, and California.
This paper develops a scaling limit theory for SGLD-Gibbs to provide principled hyperparameter tuning guidance for meaningful uncertainty quantification in large-scale latent variable models.
This paper proposes new discrete-time approximations for stochastic gradient Langevin dynamics (SGLD) with and without momentum, enabling accurate predictions of stationary covariance, iterate average covariance, and integrated autocorrelation time. The method provides improved tuning guidance for large-sample uncertainty quantification, especially under model misspecification.
This paper presents a multi-task scientific machine learning framework for turbine prognostics that jointly predicts engine health metrics and remaining useful life with quantified uncertainty, using a shared sequence encoder and task-specific heads.
This paper investigates how similar large language model uncertainty is to human uncertainty, exploring alignment, calibration, and activation patterns in LLMs across multiple datasets and the impact of instruction fine-tuning.
This paper benchmarks five uncertainty quantification methods for neural network predictions of turbine gas temperature, evaluating trade-offs in coverage, width, and stability to guide prognostics and health management in engines.
This paper introduces CAGE, a counterfactual graph-based method for calibrating multi-agent LLM systems, evaluating on benchmarks like TriviaQA and MMLU-Pro across various communication topologies. The method outperforms existing post-hoc and LLM-elicited calibration approaches.
Introduces Conf-Gen, a framework adapting conformal risk control to generative models, providing formal uncertainty guarantees for LLMs, image generators, and AI agents.
A mathematically principled framework, Variational Inference Evidential Deep Learning (VI-EDL), is proposed to address limitations in conventional Evidential Deep Learning by reformulating it through variational inference, deriving an Evidence Lower Bound, establishing a generalization bound, and achieving state-of-the-art performance on visual and medical datasets.
Introduces Neural Bayesian Sequential Routing (NBSR), a framework that models neural inference as sequential evidence accumulation over a DAG using Dirichlet-Categorical conjugate updates, enabling uncertainty quantification, early exiting, and resource-rational inference.
This paper investigates Neutrosophic Logic as a framework for modeling epistemic states in Large Language Models, demonstrating that it can capture 'hyper-truth' states beyond traditional probability constraints, leading to more transparent and ethically aware AI systems.
This paper introduces a novel uncertainty-aware PINN framework for flood inference from SAR data, addressing 'physics shock' by dynamically relaxing physical constraints in noisy regions. Evaluated on Sen1Floods11, the method achieves a 25% improvement in IoU and provides calibrated uncertainty bounds for operational disaster response.
This paper introduces an empirical Bayes conformal prediction framework that uses r-values to incorporate score variability into nonconformity scores, improving ranking stability and reducing set size while preserving coverage for vision and language models.
This paper introduces a method to calibrate uncertainty in language models by extracting eleven scale-invariant geometric features from per-layer MLP update trajectories and feeding them to a sparse linear probe, outperforming MSP under selective abstention by up to 21 AURC points.
This position paper argues that sampling-based inference in Bayesian neural networks has achieved computational parity with optimization-based methods and is poised to supersede them, offering superior uncertainty quantification and prediction performance.
This study evaluates five machine learning classifiers for chronic kidney disease risk prediction, finding that near-perfect internal performance fails under distribution shift. It emphasizes the need for calibration stability and conformal coverage transfer before clinical deployment.
PASC proposes a conformal prediction method for multi-stage NLP and LLM pipelines that provides finite-sample, distribution-free joint coverage guarantees across all stages, achieving higher empirical coverage and efficiency than baselines like Bonferroni and independent CP.
This position paper argues that current uncertainty quantification methods for large language models are essentially unsupervised clustering, measuring internal consistency rather than external correctness, and therefore fail to detect confident hallucinations. The authors advocate for a paradigm shift to ground uncertainty in objective truth.
Proposes a bi-level chaotic fusion based graph convolutional network for stock market prediction intervals, achieving significant improvements in Winkler score, PIAW, and PICP over baselines on NSE data from 2016-2026.
Njord is a probabilistic graph neural network for ensemble ocean forecasting that provides uncertainty estimates and achieves state-of-the-art performance on global and regional benchmarks, improving surface temperature prediction.