EnergyMamba proposes an uncertainty-aware, graph-enhanced selective state space model to significantly improve both the accuracy and reliability of energy consumption prediction by explicitly modeling…

This paper proposes a framework, UBG-Net, for robust audio-visual speech recognition using a Modality Uncertainty-aware Bayesian Fusion mechanism and Distribution Uncertainty-aware Hierarchical Voting…

This paper proposes a method to improve error prediction for LLMs by explicitly disentangling input ambiguity from standard Uncertainty Quantification signals, showing that ambiguity information signi…

The paper proposes Shapley-based input uncertainty Quantification (ShaQ), a novel framework that uses Shapley values to precisely attribute input-induced uncertainty to specific spans of text, providi…

This paper presents a framework for learning minimal Linear Temporal Logic (LTL) formulas from uncertain system demonstrations, reducing the problem to Pseudo-Boolean Optimization.

This paper investigates whether model compression techniques (like quantization and pruning) preserve a Large Language Model's ability to quantify its own uncertainty, finding that accuracy-only evalu…

This paper benchmarks five distinct uncertainty quantification methods—including Delta, Bayesian Dropout, and Bootstrap—to determine the optimal approach for predicting turbine gas temperature degrada…

The paper proposes Sensitivity-Uncertainty Alignment (SUA), a framework that measures the misalignment between a model's prediction instability and its stated uncertainty to improve model reliability.

The paper proposes CoMet, a method for uncertainty estimation in multimodal large language models, which decomposes uncertainty into context-specific and multiplicity-specific terms.

This paper proposes a hierarchical Bayesian model and an efficient MCMC algorithm to tackle ill-posed inverse problems in the presence of non-linear forward models, additive and multiplicative noise,…

The paper proposes Under-Cali, an uncertainty-driven dual-expert calibration framework, to achieve stable and efficient online forecasting for irregularly sampled multivariate time series.

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

The paper introduces a comprehensive framework, Realtime Risk Studio, that operationalizes qualitative risk models (Bowtie diagrams) into formal, probabilistic, and intervention-ready runtime models u…

This paper investigates whether large language models exhibit uncertainty signals similar to human judgment, examining both overt behavior and internal activation patterns to assess alignment and cali…

The paper introduces CROP, a novel conformal procedure that provides rigorous statistical guarantees for certifying the longest safe prefix of a language model's reasoning trace, allowing for targeted…

This paper presents a unified framework for end-to-end co-design of neural network processors.

The paper proposes an uncertainty-aware transfer learning framework using the Temporal Fusion Transformer (TFT) to achieve robust and scalable energy forecasting across different buildings, demonstrat…