{"total":59,"rows":[{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86,"area":null},{"id":"2402.09963","title":"Why are Sensitive Functions Hard for Transformers?","created":"2024-02-15","cited_by_count":74,"area":null},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29,"area":null},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2405.20131","title":"Language Models Need Inductive Biases to Count Inductively","created":"2024-05-30","cited_by_count":25,"area":null},{"id":"2407.03310","title":"Universal Length Generalization with Turing Programs","created":"2024-07-03","cited_by_count":25,"area":null},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24,"area":null},{"id":"2405.20671","title":"Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2306.16921","title":"Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2402.04875","title":"On Provable Length and Compositional Generalization","created":"2024-02-07","cited_by_count":22,"area":null},{"id":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20,"area":null},{"id":"2301.13833","title":"A Mathematical Model for Curriculum Learning for Parities","created":"2023-01-31","cited_by_count":19,"area":null},{"id":"2411.12892","title":"Selective Attention: Enhancing Transformer through Principled Context Control","created":"2024-11-19","cited_by_count":16,"area":null},{"id":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2310.00726","title":"Improving Length-Generalization in Transformers via Task Hinting","created":"2023-10-01","cited_by_count":13,"area":null},{"id":"2409.17555","title":"Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler","created":"2024-09-26","cited_by_count":12,"area":null},{"id":"2404.00560","title":"A Theory for Length Generalization in Learning to Reason","created":"2024-03-31","cited_by_count":11,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2310.08866","title":"Adaptivity and Modularity for Efficient Generalization Over Task Complexity","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2406.02847","title":"Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2403.11963","title":"Transfer Learning Beyond Bounded Density Ratios","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2407.11542","title":"Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2505.21785","title":"Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2410.23461","title":"Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2606.29983","title":"Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping","created":"2026-06-29","cited_by_count":4,"area":null},{"id":"2409.12446","title":"Neural Networks Generalize on Low Complexity Data","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2411.01035","title":"Provable Length Generalization in Sequence Prediction via Spectral Filtering","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2602.08907","title":"Positive Distribution Shift as a Framework for Understanding Tractable Learning","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2410.08898","title":"Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2410.17161","title":"Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2510.13680","title":"Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2512.00940","title":"Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2603.19954","title":"On the Ability of Transformers to Verify Plans","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2406.06354","title":"On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2407.18601","title":"Reorganizing attention-space geometry with expressive attention","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2603.11161","title":"Algorithmic Task Capture, Computational Complexity, and Inductive Bias of Infinite Transformers","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.10019","title":"The two clocks and the innovation window: When and how generative models learn rules","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.10237","title":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.08768","title":"Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2608.00418","title":"Making Transformers Logical","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2312.05698","title":"Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning","created":"2023-12-09","cited_by_count":0,"area":null},{"id":"2502.00197","title":"Learning Model Successors","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2507.09897","title":"Algorithm Development in Neural Networks: Insights from the Streaming Parity Task","created":"2025-07-14","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":"2510.04130","title":"On the Limitations and Capabilities of Position Embeddings for Length Generalization","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2605.00817","title":"When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.22972","title":"A mathematical theory of balancing relational generalization and memorization","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.29823","title":"Quantifying and Optimizing Simplicity via Polynomial Representations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.16528","title":"Hierarchical Domain Generalization","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.15971","title":"The Limits of Binding in Dual Encoders","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}