Related papers: Useful Evaluation: Syntax and Semantics (Technical…

To interpret deep models' predictions, attention-based visual cues are widely used in addressing \textit{why} deep models make such predictions. Beyond that, the current research community becomes more interested in reasoning \textit{how}…

Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a critical bottleneck. While Key-Value (KV) caching effectively…

We present a new Unbiased Minimal Variance (UMV) estimator for the purpose of reconstructing the large--scale structure of the universe from noisy, sparse and incomplete data. Similar to the Wiener Filter (WF), the UMV estimator is derived…

In this paper we address the problem of decision making within a Markov decision process (MDP) framework where risk and modeling errors are taken into account. Our approach is to minimize a risk-sensitive conditional-value-at-risk (CVaR)…

In this paper, we define and analyze a subclass of (time-invariant) Control Barrier Functions (CBF) that have favorable properties for the construction of uniformly timevarying CBFs and thereby for the satisfaction of uniformly time-varying…

Open-ended grading is central to equitable and personalized education, yet manual grading remains time-consuming and costly, underscoring the need for automated grading systems. Although recent neural and large language model (LLM) based…

Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However, existing CBMs and their variants have two crucial…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

In this article, variational state estimation is examined from the dynamic programming perspective. This leads to two different value functional recursions depending on whether backward or forward dynamic programming is employed. The result…

Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains. An established approach to interpretability is generating visual attribution maps that…

One principled approach for provably efficient exploration is incorporating the upper confidence bound (UCB) into the value function as a bonus. However, UCB is specified to deal with linear and tabular settings and is incompatible with…

This article presents a systematic method for designing time-varying Control Barrier Functions (CBF) composed of a time-invariant component and multiple time-dependent components, leveraging structural properties of the system dynamics. The…

Reversible computation requires that intermediate data be explicitly undone rather than discarded. In quantum programming, this principle appears as uncomputation, usually treated as a technical cleanup mechanism. We instead present…

Continual learning remains a challenge across various natural language processing (NLP) tasks, as models updated with new training data often risk catastrophic forgetting of previously acquired knowledge. We introduce a discrete key-value…

Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevailing paradigms typically rely on solitary rollout strategies where…

Partially Observable Markov Decision Processes (POMDPs) are fundamental to decision-making under uncertainty. We introduce a novel scalable approach to accelerate upper bound estimation in Point-Based Value Iteration (PBVI) algorithms, the…

We present an unsupervised explainable word embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a word using human-readable labels,…

This paper analyzes the computational complexity of validated interval methods for uncertain nonlinear systems and steady-state enclosure. Interval analysis produces guaranteed enclosures that account for uncertainty and round-off, but its…

Classification is a well-studied machine learning task which concerns the assignment of instances to a set of outcomes. Classification models support the optimization of managerial decision-making across a variety of operational business…