{"total":45,"rows":[{"id":"2409.17858","title":"How Feature Learning Can Improve Neural Scaling Laws","created":"2024-09-26","cited_by_count":56,"area":null},{"id":"2509.23024","title":"Tracing the Representation Geometry of Language Models from Pretraining to Post-training","created":"2025-09-27","cited_by_count":35,"area":null},{"id":"2402.04362","title":"Neural Networks Learn Statistics of Increasing Complexity","created":"2024-02-06","cited_by_count":31,"area":null},{"id":"2410.19637","title":"A distributional simplicity bias in the learning dynamics of transformers","created":"2024-10-25","cited_by_count":24,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"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":"2408.15138","title":"How transformers learn structured data: insights from hierarchical filtering","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","cited_by_count":15,"area":null},{"id":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2404.08602","title":"Sliding down the stairs: how correlated latent variables accelerate learning with neural networks","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2409.13904","title":"High-dimensional learning of narrow neural networks","created":"2024-09-20","cited_by_count":12,"area":null},{"id":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2603.00742","title":"To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters","created":"2026-02-28","cited_by_count":10,"area":null},{"id":"2310.02396","title":"Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2405.18296","title":"Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2303.02034","title":"Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies","created":"2023-03-03","cited_by_count":7,"area":null},{"id":"2503.23896","title":"Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2410.05448","title":"Task Diversity Shortens the ICL Plateau","created":"2024-10-07","cited_by_count":5,"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":"2312.14922","title":"Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2406.17467","title":"Early learning of the optimal constant solution in neural networks and humans","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2404.19505","title":"Context-Aware Machine Translation with Source Coreference Explanation","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2505.13567","title":"Learning Dynamics of RNNs in Closed-Loop Environments","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2507.05035","title":"Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2311.14120","title":"Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2412.06545","title":"On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2510.25480","title":"Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.21715","title":"DNNs, Dataset Statistics, and Correlation Functions","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2602.04832","title":"It's Not a Lottery, It's a Race: Understanding How Gradient Descent Adapts the Network's Capacity to the Task","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2608.23573","title":"Data Predictability Shapes Weibull Weight-Scale Growth in Transformer Training","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2303.01429","title":"Optimal transfer protocol by incremental layer defrosting","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2307.04841","title":"Loss Dynamics of Temporal Difference Reinforcement Learning","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2510.04285","title":"Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2512.13707","title":"Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.02153","title":"Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.01288","title":"A Theory of Saddle Escape in Deep Nonlinear Networks","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.07844","title":"Distributional simplicity bias and effective convexity in Energy Based Models","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.16913","title":"A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.19178","title":"Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.20276","title":"OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.26973","title":"Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29152","title":"Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}