{"total":52,"rows":[{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2412.02975","title":"Theoretical limitations of multi-layer Transformer","created":"2024-12-04","cited_by_count":45,"area":null},{"id":"2408.14332","title":"One-layer transformers fail to solve the induction heads task","created":"2024-08-26","cited_by_count":32,"area":null},{"id":"2503.10084","title":"Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs","created":"2025-03-13","cited_by_count":31,"area":null},{"id":"2411.06646","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","created":"2024-11-11","cited_by_count":30,"area":null},{"id":"2406.09347","title":"Separations in the Representational Capabilities of Transformers and Recurrent Architectures","created":"2024-06-13","cited_by_count":29,"area":null},{"id":"2504.04011","title":"Foundation Models for Time Series: A Survey","created":"2025-04-05","cited_by_count":23,"area":null},{"id":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2412.09925","title":"Simulating Hard Attention Using Soft Attention","created":"2024-12-13","cited_by_count":15,"area":null},{"id":"2603.26554","title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","created":"2026-03-27","cited_by_count":14,"area":null},{"id":"2410.23506","title":"The Belief State Transformer","created":"2024-10-30","cited_by_count":12,"area":null},{"id":"2506.16055","title":"Knee-Deep in C-RASP: A Transformer Depth Hierarchy","created":"2025-06-19","cited_by_count":12,"area":null},{"id":"2602.03655","title":"Sequential Group Composition: A Window into the Mechanics of Deep Learning","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2410.11474","title":"How Transformers Get Rich: Approximation and Dynamics Analysis","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2411.19574","title":"KV Shifting Attention Enhances Language Modeling","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2502.15801","title":"An explainable transformer circuit for compositional generalization","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2406.02585","title":"Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2411.15671","title":"Best of Both Worlds: Advantages of Hybrid Graph Sequence Models","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2506.05200","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2407.16153","title":"On the Benefits of Rank in Attention Layers","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2505.14840","title":"Subquadratic Algorithms and Hardness for Attention with Any Temperature","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2602.04768","title":"Billion-Scale Graph Foundation Models","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2411.13028","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2503.11272","title":"When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2509.09001","title":"Fast attention mechanisms: a tale of parallelism","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2506.12220","title":"Two Heads Are Better than One: Simulating Large Transformers with Small Ones","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2605.22471","title":"Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2503.06917","title":"Sample-Efficient Optimization over Generative Priors via Coarse Learnability","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2602.01763","title":"A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.10848","title":"Transformers Learn Latent Mixture Models In-Context via Mirror Descent","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2605.08453","title":"Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.31423","title":"Fixed Universal Transformers","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.02800","title":"Induction Heads Interpolate N-Grams","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2406.01424","title":"Universal In-Context Approximation By Prompting Fully Recurrent Models","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2410.09867","title":"Towards characterizing the value of edge embeddings in Graph Neural Networks","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2502.00197","title":"Learning Model Successors","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2509.23178","title":"Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.18638","title":"Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2602.13155","title":"Learning to Approximate Uniform Facility Location via Graph Neural Networks","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.11332","title":"On the Computational Hardness of Transformers","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.28499","title":"Next-Token Prediction and Regret Minimization","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.24878","title":"Transformer Approximations from ReLUs","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.17930","title":"InfoFlow: A Framework for Multi-Layer Transformer Analysis","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.11673","title":"Higher-Order Token Interactions via Quantum Attention","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.11427","title":"Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.36221","title":"How Language Models Differ in Redistributing Attention-Head Activity Under Serial Demand","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36585","title":"Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38446","title":"What Pretraining and Midtraining Make Learnable from Rewards?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14456","title":"Learning to Extrapolate in Depth with Looped Transformers","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}