{"total":18,"rows":[{"id":"2306.03009","title":"Using Sequences of Life-events to Predict Human Lives","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2404.07647","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","created":"2024-04-11","cited_by_count":21,"area":null},{"id":"2203.06462","title":"Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice","created":"2022-03-12","cited_by_count":15,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2603.10145","title":"Lost in Backpropagation: The LM Head is a Gradient Bottleneck","created":"2026-03-10","cited_by_count":9,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2305.04782","title":"HistAlign: Improving Context Dependency in Language Generation by Aligning with History","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2110.05409","title":"Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling","created":"2021-10-11","cited_by_count":3,"area":null},{"id":"2101.07077","title":"Yet Another Representation of Binary Decision Trees: A Mathematical Demonstration","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2203.12693","title":"Enhancing Classifier Conservativeness and Robustness by Polynomiality","created":"2022-03-23","cited_by_count":1,"area":null},{"id":"2412.12894","title":"Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2506.22271","title":"On the Theoretical Limitations of Embedding-based Link Prediction","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2608.14691","title":"The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2101.11347","title":"Decision Machines: Congruent Decision Trees","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2108.12115","title":"Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2508.03175","title":"Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2602.17898","title":"Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2610.19247","title":"Copy-Paste Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}