English
Related papers

Related papers: Unsupervised Grounding of Plannable First-Order Lo…

200 papers

Classical AI planners provide solutions to planning problems in the form of long and opaque text outputs. To aid in the understanding transferability of planning solutions, it is necessary to have a rich and comprehensible representation…

Artificial Intelligence · Computer Science 2021-07-14 Angeline Aguinaldo , William Regli

Logical reasoning is central to complex human activities, such as thinking, debating, and planning; it is also a central component of many AI systems as well. In this paper, we investigate the extent to which encoder-only transformer…

Computation and Language · Computer Science 2024-07-02 Paulo Pirozelli , Marcos M. José , Paulo de Tarso P. Filho , Anarosa A. F. Brandão , Fabio G. Cozman

Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based…

Machine Learning · Computer Science 2022-11-21 Sindy Löwe , Phillip Lippe , Maja Rudolph , Max Welling

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

Computation and Language · Computer Science 2026-05-29 Pierre-Antoine Lequeu , Camille Barboule , Benjamin Piwowarski

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the…

Computation and Language · Computer Science 2020-10-12 Zuchao Li , Hai Zhao , Rui Wang , Kevin Parnow

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Quantitative Methods · Quantitative Biology 2026-01-21 Xiangyu Liu , Haodi Lei , Yi Liu , Yang Liu , Wei Hu

Unsupervised learning has been widely applied to various tasks in particle physics. However, existing models lack precise control over their learned representations, limiting physical interpretability and hindering their use for accurate…

High Energy Physics - Experiment · Physics 2025-12-01 Xing-Jian Lv , De-Xing Miao , Zi-Jun Xu , Jian-Chun Wang

In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly…

Machine Learning · Computer Science 2020-11-11 Massimiliano Patacchiola , Amos Storkey

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Nilaksh , Saurav Jha , Artem Zholus , Sarath Chandar

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

We present VAEL, a neuro-symbolic generative model integrating variational autoencoders (VAE) with the reasoning capabilities of probabilistic logic (L) programming. Besides standard latent subsymbolic variables, our model exploits a…

Programming Languages · Computer Science 2022-05-26 Eleonora Misino , Giuseppe Marra , Emanuele Sansone

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Artificial Intelligence · Computer Science 2026-05-15 Leslie G. Valiant

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

Astrophysics of Galaxies · Physics 2020-09-30 Miguel A. Aragon-Calvo

Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available. However, deep learning solely focuses on the accuracy of the predictions, neglecting the reasoning process…

Artificial Intelligence · Computer Science 2020-02-07 Giuseppe Marra , Michelangelo Diligenti , Francesco Giannini , Marco Gori , Marco Maggini

Vision-language-action (VLA) models typically inject proprioception only as a late conditioning signal, which prevents robot state from shaping instruction understanding and from influencing which visual tokens are attended throughout the…

Robotics · Computer Science 2026-02-09 Fangyuan Wang , Peng Zhou , Jiaming Qi , Shipeng Lyu , David Navarro-Alarcon , Guodong Guo

First-order logic is typically presented as the study of deduction in a setting with elementary quantification. In this paper, we take another vantage point and conceptualize first-order logic as a linear space that encodes "plausibility".…

Logic in Computer Science · Computer Science 2020-01-31 Daniel Huang

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Artificial Intelligence · Computer Science 2026-03-27 Yunpeng Zhou

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

In many probabilistic first-order representation systems, inference is performed by "grounding"---i.e., mapping it to a propositional representation, and then performing propositional inference. With a large database of facts, groundings…

Artificial Intelligence · Computer Science 2013-05-13 William Yang Wang , Kathryn Mazaitis , William W. Cohen

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier
‹ Prev 1 3 4 5 6 7 10 Next ›