English
Related papers

Related papers: TokenBlowUp: Resolving Representational Singularit…

200 papers

Large language models (LLMs) excel in many natural language tasks, yet they struggle with complex mathemat-ical problem-solving, particularly in symbolic reasoning and maintaining consistent output. This study evalu-ates 10 LLMs with 7 to 8…

Machine Learning · Computer Science 2025-01-29 Evgenii Evstafev

Advances in large language models (LLMs) are accelerating discovery in molecular science. However, adapting molecular information to the serialized, token-based processing of LLMs remains a key challenge. Compared to other representations,…

Chemical Physics · Physics 2025-12-04 Mingxu Zhang , Dazhong Shen , Ying Sun

In this paper, we construct a combined multiscale finite element method (MsFEM) using the Local Orthogonal Decomposition (LOD) technique to solve the multiscale problems which may have singularities in some special portions of the…

Numerical Analysis · Mathematics 2022-09-14 Kuokuo Zhang , Weibing Deng , Haijun Wu

We study spherical charged black holes in the presence of a cosmological constant with corrections motivated by the theory of loop quantum gravity. The effective theory is constructed at the Hamiltonian level by introducing certain…

General Relativity and Quantum Cosmology · Physics 2023-04-12 Asier Alonso-Bardaji , David Brizuela , Raül Vera

With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically…

Computation and Language · Computer Science 2024-04-22 Yuxi Li , Yi Liu , Gelei Deng , Ying Zhang , Wenjia Song , Ling Shi , Kailong Wang , Yuekang Li , Yang Liu , Haoyu Wang

Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However, these approaches typically treat the problem as a generic image-to-image regression on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Qianlei Wang , Kexun Chen , Shaolin Zhang , Hongli Gao , Chaoning Zhang , Xiaolin Qin

The transformer architecture has become the foundation of modern Large Language Models (LLMs), yet its theoretical properties are still not well understood. As with classic neural networks, a common approach to improve these models is to…

Artificial Intelligence · Computer Science 2025-09-26 Álvaro Rodríguez Abella , João Pedro Silvestre , Paulo Tabuada

Recent advancements in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing diverse data types, yet significant disparities persist between human cognitive processes and computational approaches…

Computation and Language · Computer Science 2025-05-09 Dongxing Yu

LLM pre-training efficacy increasingly depends on data composition rather than sheer volume. Yet, optimal mixing is hindered by categorization flaws: human taxonomies suffer from ontological misalignment, and Euclidean clustering fails to…

Machine Learning · Computer Science 2026-05-27 Yue Min , Ziyun Qiao , Ruining Chen , Yujun Li

The problem of resolution of singularities in positive characteristic can be reformulated as follows: Fix a hypersurface $X$, embedded in a smooth scheme, with points of multiplicity at most $n$. Let an $n$-sequence of transformations of…

Algebraic Geometry · Mathematics 2011-03-18 Angélica Benito , Orlando E. Villamayor

In this paper, we develop the blow-up analysis and establish the energy quantization for solutions to super-Liouville type equations on Riemann surfaces with conical singularities at the boundary. In other problems in geometric analysis,…

Differential Geometry · Mathematics 2019-08-27 Jürgen Jost , Chunqin Zhou , Miaomiao Zhu

We consider the semilinear wave equation with power nonlinearity in one space dimension. Given a blow-up solution with a characteristic point, we refine the blow-up behavior first derived by Merle and Zaag. We also refine the geometry of…

Analysis of PDEs · Mathematics 2012-04-25 Raphaël Côte , Hatem Zaag

Internal representations within deep neural architectures encode high-dimensional abstractions of linguistic structures, yet they often exhibit inefficiencies in feature distribution, limiting expressiveness and adaptability. Contextual…

Computation and Language · Computer Science 2025-03-27 Alistair Wren , Beatrice Loxley , Hamish Cadwallader , Simon Beckwith , Fabian Pargeter , James Blades

Our concerns here are blow-up solutions for ODEs with exponential nonlinearity from the viewpoint of dynamical systems and their numerical validations. As an example, the finite difference discretization of $u_t = u_{xx} + e^{u^m}$ with the…

Numerical Analysis · Mathematics 2019-02-06 Kaname Matsue , Akitoshi Takayasu

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but continue to struggle with geometric reasoning, primarily due to the perception bottleneck regarding fine-grained visual elements. While formal languages have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Peijie Wang , Ming-Liang Zhang , Jun Cao , Chao Deng , Dekang Ran , Hongda Sun , Pi Bu , Xuan Zhang , Yingyao Wang , Jun Song , Bo Zheng , Fei Yin , Cheng-Lin Liu

In this paper, we study general Toda systems with homogeneous Neumann boundary conditions on Riemann surfaces. Assuming the surface satisfies the ``$k$-symmetric'' condition, we construct a family of bubbling solutions using singular…

Analysis of PDEs · Mathematics 2026-03-16 Zhengni Hu , Miaomiao Zhu

The idea in the title is to blow up a finite structure, replacing each 'colour or atom' by infinitely many, using blurs to represent the resulting term algebra, but the blurs are not enough to blur the structure of the finite structure in…

Logic · Mathematics 2013-04-19 Tarek Sayed Ahmed

Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance…

Artificial Intelligence · Computer Science 2025-10-28 Nannan Shi , Chuanyu Qin , Shipeng Song , Man Luo

Enabling large language models (LLMs) to effectively process and reason with graph-structured data remains a significant challenge despite their remarkable success in natural language tasks. Current approaches either convert graph…

Artificial Intelligence · Computer Science 2025-09-03 Yanbiao Ji , Chang Liu , Xin Chen , Dan Luo , Mei Li , Yue Ding , Wenqing Lin , Hongtao Lu

Despite the evident necessity of topological protection for realizing scalable quantum computers, the conceptual underpinnings of topological quantum logic gates had arguably remained shaky, both regarding their physical realization as well…

Quantum Physics · Physics 2024-07-12 David Jaz Myers , Hisham Sati , Urs Schreiber