English
Related papers

Related papers: THEIA: Learning Complete Kleene Three-Valued Logic…

200 papers

This paper compares three methodological categories of neural reasoning: LLM reasoning, supervised learning-based reasoning, and explicit model-based reasoning. LLMs remain unreliable and struggle with simple decision-making that animals…

Artificial Intelligence · Computer Science 2026-01-05 Tiansi Dong , Henry He , Pietro Liò , Mateja Jamnik

Probabilistic logical models are a core component of neurosymbolic AI and are important in their own right for tasks that require high explainability. Unlike neural networks, logical theories that underlie the model are often handcrafted…

Artificial Intelligence · Computer Science 2025-10-07 Jonathan Feldstein , Dominic Phillips , Efthymia Tsamoura

Generative AI (GenAI) is increasingly used as a knowledge partner in higher education, raising the need for instructional designs that emphasize AI literacy practices such as evaluating output credibility and maintaining human…

Human-Computer Interaction · Computer Science 2026-03-30 Md Touhidul Islam , Mahir Akgun , Syed Billah

Current AI safety relies on behavioral monitoring and post-training alignment, yet empirical measurement shows these approaches produce no detectable pre-commitment signal in a majority of instruction-tuned models tested. We present an…

Artificial Intelligence · Computer Science 2026-04-07 Gregory M. Ruddell

Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion…

Machine Learning · Computer Science 2024-08-07 Sangamesh Kodge , Gobinda Saha , Kaushik Roy

While modern transformer neural networks achieve grandmaster-level performance in chess and other reasoning tasks, their internal computation process remains largely opaque. Focusing on Leela Chess Zero (LC0), we introduce a sparse…

Machine Learning · Computer Science 2026-04-14 Rui Lin , Zhenyu Jin , Guancheng Zhou , Xuyang Ge , Wentao Shu , Jiaxing Wu , Junxuan Wang , Zhengfu He , Junping Zhang , Xipeng Qiu

We continue earlier efforts in computing the dimensions of tangent space cohomologies of Calabi-Yau manifolds using deep learning. In this paper, we consider the dataset of all Calabi-Yau four-folds constructed as complete intersections in…

High Energy Physics - Theory · Physics 2021-11-16 Harold Erbin , Riccardo Finotello , Robin Schneider , Mohamed Tamaazousti

Reinforcement-learned reasoning has powered recent AI leaps on verifiable tasks, including mathematics, code, and structure prediction. The harder bottleneck is evaluative judgment in low-verifiability domains, where no oracle anchors…

Artificial Intelligence · Computer Science 2026-05-15 Ziqin Gong , Ning Li , Huaikang Zhou

Extremely Large-scale Array (ELAA) is considered a frontier technology for future communication systems, pivotal in improving wireless systems' rate and spectral efficiency. As ELAA employs a multitude of antennas operating at higher…

Machine Learning · Computer Science 2024-08-26 Jiali Nie , Yuanhao Cui , Zhaohui Yang , Weijie Yuan , Xiaojun Jing

Prediction and discovery of new materials with desired properties are at the forefront of quantum science and technology research. A major bottleneck in this field is the computational resources and time complexity related to finding new…

This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds via gradient descent, unlike conventional methods where they…

Machine Learning · Computer Science 2021-03-22 Kambiz Azarian , Yash Bhalgat , Jinwon Lee , Tijmen Blankevoort

Classical deep networks are effective because depth enables adaptive geometric deformation of data representations. In quantum neural networks (QNNs), however, depth or state reachability alone does not guarantee this feature-learning…

Quantum Physics · Physics 2026-03-26 Vishal S. Ngairangbam , Michael Spannowsky

We present that hierarchical LLM reasoning via scaling thought templates can effectively optimize the reasoning search space and outperform the mathematical reasoning capabilities of powerful LLMs like OpenAI o1-preview and DeepSeek V3. We…

Computation and Language · Computer Science 2025-03-12 Ling Yang , Zhaochen Yu , Bin Cui , Mengdi Wang

When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative Agreement (GEA), a validity criterion measuring whether an LLM's scoring…

Artificial Intelligence · Computer Science 2026-05-20 Grandee Lee , Yue Wang , Che Yee Lye , Luke Peh

The accuracy and complexity of machine learning algorithms based on kernel optimization are limited by the set of kernels over which they are able to optimize. An ideal set of kernels should: admit a linear parameterization (for…

Machine Learning · Computer Science 2020-06-16 Brendon K. Colbert , Matthew M. Peet

The EU AI Act (EUAIA) introduces requirements for AI systems which intersect with the processes required to establish adversarial robustness. However, given the ambiguous language of regulation and the dynamicity of adversarial attacks,…

Computation and Language · Computer Science 2024-10-15 Tomas Bueno Momcilovic , Dian Balta , Beat Buesser , Giulio Zizzo , Mark Purcell

Training large foundation models costs hundreds of millions of dollars, making deployment optimization critical. Current approaches require machine learning engineers to manually craft training recipes through error-prone trial-and-error on…

AI text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary. On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834…

Machine Learning · Computer Science 2026-05-22 Alexander Smirnov

Deep Neural Networks (DNNs) are widely employed in safety-critical domains, where ensuring their reliability is essential. Triple Modular Redundancy (TMR) is an effective technique to enhance the reliability of DNNs in the presence of…

Machine Learning · Computer Science 2025-07-15 Kimia Soroush , Nastaran Shirazi , Mohsen Raji

How does the neocortex learn and develop the foundations of all our high-level cognitive abilities? We present a comprehensive framework spanning biological, computational, and cognitive levels, with a clear theoretical continuity between…

Neurons and Cognition · Quantitative Biology 2017-09-15 Randall C. O'Reilly , Dean R. Wyatte , John Rohrlich