Related papers: Exploring the Structure of Misconceptions in the F…

Mixture-of-Experts (MoE) architectures have emerged as a promising direction, offering efficiency and scalability by activating only a subset of parameters during inference. However, current research remains largely performance-centric,…

Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction. Therefore, CFs can be used as (i) interventions for…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-trained offline on small, simulated training sets from a…

Community detection techniques are widely used to infer hidden structures within interconnected systems. Despite demonstrating high accuracy on benchmarks, they reproduce the external classification for many real-world systems with a…

The extraction of brain functioning features is a crucial step in the definition of brain-computer interfaces (BCIs). In the last decade, functional connectivity (FC) estimators have been increasingly explored based on their ability to…

We present a systematic benchmark of MACE potentials for iron-nickel alloys, focusing on structural, elastic, magnetic, and finite-temperature properties relevant to phase stability. The reference dataset comprises spin-polarized PBE…

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

In this paper we present a method of modeling and analysis that permits the extraction and quantitative display of detailed information about the effects of instruction on a class's knowledge. The method relies on a congitive model that…

Community detection is a significant and challenging task in network research. Nowadays, plenty of attention has been focused on local methods of community detection. Among them, community detection with a greedy algorithm typically starts…

We consider an alternate definition of community structure that is functionally motivated. We define network community structure-based on the function the network system is intended to perform. In particular, as a specific example of this…

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to…

Learning about underlying patterns in data using latent unobserved structures to improve the accuracy of predictive models has become an active avenue of deep learning research. Most approaches cluster the original features to capture…

Machine-learning force fields (MLFFs) have emerged as a promising solution for speeding up ab initio molecular dynamics (MD) simulations, where accurate force predictions are critical but often computationally expensive. In this work, we…

Counterfactual explanations describe how to modify a feature vector in order to flip the outcome of a trained classifier. Obtaining robust counterfactual explanations is essential to provide valid algorithmic recourse and meaningful…

High-stakes exams play a large role in determining an introductory physics student's final grade. These exams have been shown to be inequitable, often to the detriment of students identifying with groups historically marginalized in…

Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to…

When training and evaluating machine reading comprehension models, it is very important to work with high-quality datasets that are also representative of real-world reading comprehension tasks. This requirement includes, for instance,…

Models of physical systems are used to explain and predict experimental results and observations. When students encounter discrepancies between the actual and expected behavior of a system, they revise their models to include the newly…

Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information. Recently, CIL based on pre-trained models (PTMs) has achieved…