English
Related papers

Related papers: Internalizing Tools as Morphisms in Graded Transfo…

200 papers

A recent trend in probabilistic inference emphasizes the codification of models in a formal syntax, with suitable high-level features such as individuals, relations, and connectives, enabling descriptive clarity, succinctness and…

Artificial Intelligence · Computer Science 2016-06-15 Martin Mladenov , Vaishak Belle , Kristian Kersting

Deep learning optimization exhibits structure that is not captured by worst-case gradient bounds. Empirically, gradients along training trajectories are often temporally predictable and evolve within a low-dimensional subspace. In this work…

Machine Learning · Computer Science 2026-01-09 Anherutowa Calvo

We investigate grokking in transformers through the lens of inductive bias: dispositions arising from architecture or optimization that let the network prefer one solution over another. We first show that architectural choices such as the…

Machine Learning · Computer Science 2026-02-09 Jaisidh Singh , Diganta Misra , Antonio Orvieto

Currently, prominent Transformer architectures applied on graphs and meshes for shape analysis tasks employ traditional attention layers that heavily utilize spectral features requiring costly eigenvalue decomposition-based methods. To…

Graphics · Computer Science 2025-12-09 Akis Nousias , Stavros Nousias

Robots' ability to follow language instructions and execute diverse 3D manipulation tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to…

Robotics · Computer Science 2025-03-18 Yangtao Chen , Zixuan Chen , Junhui Yin , Jing Huo , Pinzhuo Tian , Jieqi Shi , Yang Gao

Symbolic computer vision represents diagrams through explicit logical rules and structured representations, enabling interpretable understanding in machine vision. This requires fundamentally different learning paradigms from pixel-based…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Shan Zhang , Aotian Chen , Kai Zou , Jindong Gu , Yuan Xue , Anton van den Hengel

We develop a generating-function formulation for the symbolic reduction of multi-loop Feynman integrals. In this framework, integration-by-parts identities are rewritten as differential equations for sector-wise generating functions, so the…

High Energy Physics - Phenomenology · Physics 2026-05-12 Bo Feng , Xiang Li , Yuanche Liu , Yanqing Ma , Yang Zhang

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…

Computation and Language · Computer Science 2026-01-16 Guanxu Chen , Dongrui Liu , Jing Shao

Understanding the internal representations and decision mechanisms of deep neural networks remains a critical open challenge. While existing interpretability methods often identify influential input regions, they may not elucidate how a…

Machine Learning · Computer Science 2025-06-12 Farzaneh Mahdisoltani , Saeed Mahdisoltani , Roger B. Grosse , David J. Fleet

This paper investigates the possibility of approximating multiple mathematical operations in latent space for expression derivation. To this end, we introduce different multi-operational representation paradigms, modelling mathematical…

Machine Learning · Computer Science 2024-04-04 Marco Valentino , Jordan Meadows , Lan Zhang , André Freitas

We use symbolic expressions for traces of positive integer powers of a Hermitian operator (or, equivalently, coefficients of corresponding characteristic polynomial) to find solutions for the problems as follows: Factorization of…

Rings and Algebras · Mathematics 2017-08-16 Ilia Lomidze , Natela Chachava

We consider pseudodifferential operators on functions on $\R^{n+1}$ which commute with the Euler operator, and can thus be restricted to spaces of functions homogeneous of some given degree. Their symbols can be regarded as functions on a…

Representation Theory · Mathematics 2007-05-23 Michael Pevzner , André Unterberger

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Machine Learning · Computer Science 2023-01-03 Michael Chang , Thomas L. Griffiths , Sergey Levine

This paper presents a novel framework for graded neural networks (GNNs) built over graded vector spaces $\V_\w^n$, extending classical neural architectures by incorporating algebraic grading. Leveraging a coordinate-wise grading structure…

Machine Learning · Computer Science 2026-04-24 Tony Shaska

Understanding internal representations of neural models is a core interest of mechanistic interpretability. Due to its large dimensionality, the representation space can encode various aspects about inputs. To what extent are different…

Machine Learning · Computer Science 2026-05-15 Xinting Huang , Michael Hahn

Real-time autonomous systems utilize multi-layer computational frameworks to perform critical tasks such as perception, goal finding, and path planning. Traditional methods implement perception using occupancy grid mapping (OGM), segmenting…

Robotics · Computer Science 2025-02-14 Shay Snyder , Ryan Shea , Andrew Capodieci , David Gorsich , Maryam Parsa

Many patterns in nature exhibit self-similarity: they can be compactly described via self-referential transformations. Said patterns commonly appear in natural and artificial objects, such as molecules, shorelines, galaxies and even images.…

Machine Learning · Computer Science 2022-04-19 Michael Poli , Winnie Xu , Stefano Massaroli , Chenlin Meng , Kuno Kim , Stefano Ermon

Symbolic indefinite integration in Computer Algebra Systems such as Maple involves selecting the most effective algorithm from multiple available methods. Not all methods will succeed for a given problem, and when several do, the results,…

Symbolic Computation · Computer Science 2025-08-11 Rashid Barket , Matthew England , Jürgen Gerhard

I introduce a unified framework for finding a closed-form interpretation of any single neuron in an artificial neural network. Using this framework I demonstrate how to interpret neural network classifiers to reveal closed-form expressions…

Machine Learning · Computer Science 2024-10-02 Sebastian Johann Wetzel

Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concepts remain poorly understood. To bridge this gap, we propose…

Artificial Intelligence · Computer Science 2026-05-08 Zehao Deng , Tianjie Ju , Zheng Wu , Liangbo He , Jun Lan , Huijia Zhu , Weiqiang Wang , Zhuosheng Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›