{"total":33,"rows":[{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2406.00048","title":"Towards a theory of how the structure of language is acquired by deep neural networks","created":"2024-05-28","cited_by_count":39,"area":null},{"id":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2103.06872","title":"Tensor networks and efficient descriptions of classical data","created":"2021-03-11","cited_by_count":13,"area":null},{"id":"2310.06408","title":"Humans and language models diverge when predicting repeating text","created":"2023-10-10","cited_by_count":13,"area":null},{"id":"2406.05335","title":"Phase transition in large language models and the criticality of natural languages","created":"2024-06-08","cited_by_count":13,"area":null},{"id":"2503.04725","title":"L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling","created":"2025-03-06","cited_by_count":9,"area":null},{"id":"2105.05944","title":"Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay","created":"2021-05-12","cited_by_count":7,"area":null},{"id":"2112.08628","title":"Explainable Natural Language Processing with Matrix Product States","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2505.07070","title":"Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures","created":"2025-05-11","cited_by_count":5,"area":null},{"id":"2505.18373","title":"Next-token pretraining implies in-context learning","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2402.12691","title":"Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2112.06510","title":"Do Data-based Curricula Work?","created":"2021-12-13","cited_by_count":3,"area":null},{"id":"2408.06061","title":"Quantum Algorithms for Compositional Text Processing","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2503.06330","title":"States of LLM-generated Texts and Phase Transitions between them","created":"2025-03-08","cited_by_count":3,"area":null},{"id":"2508.05803","title":"Human-like fleeting memory improves language learning but impairs reading time prediction in transformer language models","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2109.13855","title":"Actionable Entities Recognition Benchmark for Interactive Fiction","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2510.21258","title":"Correlation Dimension of Auto-Regressive Large Language Models","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2402.14890","title":"Vygotsky Distance: Measure for Benchmark Task Similarity","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2505.04984","title":"Rethinking the Relationship between the Power Law and Hierarchical Structures","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2510.22109","title":"Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows","created":"2025-10-25","cited_by_count":1,"area":null},{"id":"2606.06238","title":"Generative Criticality in Large Language Model Temperature Scaling","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2208.13021","title":"On Unsupervised Training of Link Grammar Based Language Models","created":"2022-08-27","cited_by_count":0,"area":null},{"id":"2306.02334","title":"Long Text Generation Challenge","created":"2023-06-04","cited_by_count":0,"area":null},{"id":"2307.02697","title":"Strahler Number of Natural Language Sentences in Comparison with Random Trees","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2403.12969","title":"Entangling Machine Learning with Quantum Tensor Networks","created":"2024-01-09","cited_by_count":0,"area":null},{"id":"2506.00182","title":"Overfitting has a limitation: a model-independent generalization gap bound based on R\\'enyi entropy","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2512.24977","title":"SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2604.05536","title":"Turbulence-like 5/3 spectral scaling in contextual representations of language as a complex system","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2607.25184","title":"A scaling law of contextual persistence in human language","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.20912","title":"Do Quantum Models Scale Like LLMs?","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.05466","title":"Writing as a Self-Organized Critical Process","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05879","title":"Learning to Learn a Language","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}