English
Related papers

Related papers: TokenBlowUp: Resolving Representational Singularit…

200 papers

Braiding defects in topological stabiliser codes has been widely studied as a promising approach to fault-tolerant quantum computing. Here, we explore the potential and limitations of such schemes in codes of all spatial dimensions. We…

Quantum Physics · Physics 2020-08-11 Paul Webster , Stephen D. Bartlett

Despite an ever-increasing interest in topological deep learning models that target higher-order datasets, there is no consensus on how to evaluate such models. This is exacerbated by the fact that topological objects permit operations,…

Machine Learning · Computer Science 2026-05-08 Johannes S. Schmidt , Martin Carrasco , Ernst Röell , Guy Wolf , Nello Blaser , Bastian Rieck

A central question in cognitive science is whether conceptual representations converge onto a shared manifold to support generalization, or diverge into orthogonal subspaces to minimize task interference. While prior work has discovered…

Computation and Language · Computer Science 2026-02-09 Zhimin Hu , Lanhao Niu , Sashank Varma

Let $X$ be a fs logarithmic scheme that is generically logarithmically smooth, and that admits a strict closed embedding into a logarithmically smooth scheme $Y$ over a field $\kk$ of characteristic zero. We construct a simple and fast…

Algebraic Geometry · Mathematics 2023-11-21 Ming Hao Quek

We investigate the geometry of predictive information across the layers of large language models (LLMs). We repurpose representation lenses-learned affine maps trained to predict the next token from intermediate residual streams-as…

Machine Learning · Computer Science 2026-05-12 Gianfranco Lombardo , Giuseppe Trimigno , Stefano Cagnoni

We investigate topology changing processes in the WKB approximation of four dimensional quantum cosmology with a negative cosmological constant. As Riemannian manifolds which describe quantum tunnelings of spacetime we consider constant…

General Relativity and Quantum Cosmology · Physics 2009-10-28 Shuxue Ding , Yasushige Maeda , Masaru Siino

In this article we introduce a generalization of locally conformally Kaehler metrics from complex manifolds to complex analytic spaces with singularities and study which properties of locally conformally Kaehler manifolds still hold in this…

Differential Geometry · Mathematics 2019-08-14 George-Ionut Ionita , Ovidiu Preda

Testing Deep Learning (DL)-based systems is an open challenge. Although it is relatively easy to find inputs that cause a DL model to misbehave, the grouping of inputs by features that make the DL model under test fail is largely…

Machine Learning · Computer Science 2026-03-25 Gianmarco De Vita , Nargiz Humbatova , Paolo Tonella

Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters,…

Computation and Language · Computer Science 2026-02-20 Magnus Boman

We propose a novel use of Large Language Models (LLMs) as unsupervised anomaly detectors in particle physics. Using lightweight LLM-like networks with encoder-based architectures trained to reconstruct background events via masked-token…

High Energy Physics - Experiment · Physics 2026-01-28 Ambre Visive , Polina Moskvitina , Clara Nellist , Roberto Ruiz de Austri , Sascha Caron

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework…

Machine Learning · Computer Science 2026-02-04 Changhao Wang , Yunfei Yu , Xinhao Yao , Jiaolong Yang , Riccardo Cantoro , Chaobo Li , Qing Cui , Jun Zhou

AlphaGeometry represents a milestone in neuro-symbolic reasoning, yet its architecture faces a log-linear scaling bottleneck within its symbolic deduction engine that limits its efficiency as problem complexity increases. Recent technical…

Artificial Intelligence · Computer Science 2026-04-21 Anthony Bordg

Long-horizon execution in Large Language Models (LLMs) remains unstable even when high-level strategies are provided. Evaluating on controlled algorithmic puzzles, we demonstrate that while decomposition is essential for stability, extreme…

Artificial Intelligence · Computer Science 2026-04-23 Denys Pushkin , Emmanuel Abbe

Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most powerful large language models (LLMs). To study these…

Artificial Intelligence · Computer Science 2026-03-13 Mayug Maniparambil , Nils Hoehing , Janak Kapuriya , Arjun Karuvally , Ellen Rushe , Anthony Ventresque , Noel O'Connor , Fergal Reid

In supersymmetric quantum mechanics the emergence of a singularity may lead to the breakdown of isospectrality between partner potentials. One of the regularization recipes is based on a topologically nontrivial, multisheeted complex…

Quantum Physics · Physics 2011-03-14 Miloslav Znojil

Most models of generative AI for images assume that images are inherently low-dimensional objects embedded within a high-dimensional space. Additionally, it is often implicitly assumed that thematic image datasets form smooth or piecewise…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Leah Bar , Liron Mor Yosef , Shai Zucker , Neta Shoham , Inbar Seroussi , Nir Sochen

A differential geometric approach to singular perturbation theory is presented. It is shown that singular perturbation problems such as multiple-scale and boundary layer problems can be treated more easily on a differential geometric basis.…

Mathematical Physics · Physics 2008-11-06 F. Jamitzky

We show the existence of nonautonomous invariant manifolds for planar, asymptotically autonomous differential equations, that have equilibrium solutions with zero Lyapunov spectrum. These invariant manifolds correspond to the stable and…

Dynamical Systems · Mathematics 2021-11-08 Luca Arcidiacono , Christian Kuehn

We study the blow-ups of configuration spaces. These spaces have a structure of what we call an Orlik-Solomon manifold; it allows us to compute the intersection cohomology of certain flat connections with logarithmic singularities using…

Algebraic Geometry · Mathematics 2013-10-01 M. Falk , V. Schechtman , A. Varchenko

We study the geometric structure of layer updates in deep language models. Rather than analyzing what information is encoded in intermediate representations, we ask how representations change from one layer to the next. We show that…

Machine Learning · Computer Science 2026-04-06 Jun-Sik Yoo
‹ Prev 1 3 4 5 6 7 10 Next ›