{"total":171,"rows":[{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378,"area":null},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2106.15933","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","created":"2021-06-30","cited_by_count":85,"area":null},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71,"area":null},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57,"area":null},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50,"area":null},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49,"area":null},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46,"area":null},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2312.05355","title":"Neither hype nor gloom do DNNs justice","created":"2023-12-08","cited_by_count":40,"area":null},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40,"area":null},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2202.00565","title":"Data-driven emergence of convolutional structure in neural networks","created":"2022-02-01","cited_by_count":29,"area":null},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28,"area":null},{"id":"2208.14673","title":"Incremental Learning in Diagonal Linear Networks","created":"2022-08-31","cited_by_count":28,"area":null},{"id":"2201.02115","title":"The dynamics of representation learning in shallow, non-linear autoencoders","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2206.04613","title":"Explicit Regularization in Overparametrized Models via Noise Injection","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2505.17863","title":"The emergence of sparse attention: impact of data distribution and benefits of repetition","created":"2025-05-23","cited_by_count":25,"area":null},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24,"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":"2110.04947","title":"Towards Demystifying Representation Learning with Non-contrastive Self-supervision","created":"2021-10-11","cited_by_count":23,"area":null},{"id":"2305.01604","title":"The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold","created":"2023-05-02","cited_by_count":21,"area":null},{"id":"2404.12008","title":"How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2211.16980","title":"Infinite-width limit of deep linear neural networks","created":"2022-11-29","cited_by_count":20,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2405.20236","title":"Disentangling and Mitigating the Impact of Task Similarity for Continual Learning","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2405.13456","title":"Deep linear networks for regression are implicitly regularized towards flat minima","created":"2024-05-22","cited_by_count":17,"area":null},{"id":"2110.04662","title":"Cognitively Inspired Learning of Incremental Drifting Concepts","created":"2021-10-09","cited_by_count":16,"area":null},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2508.12837","title":"Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points","created":"2025-08-18","cited_by_count":16,"area":null},{"id":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","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":"2210.04643","title":"Critical Learning Periods for Multisensory Integration in Deep Networks","created":"2022-10-06","cited_by_count":14,"area":null},{"id":"2309.13989","title":"A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2409.14981","title":"On The Specialization of Neural Modules","created":"2024-09-23","cited_by_count":14,"area":null},{"id":"2501.17745","title":"Dynamics of Transient Structure in In-Context Linear Regression Transformers","created":"2025-01-29","cited_by_count":14,"area":null},{"id":"2502.03350","title":"Optimal Task Order for Continual Learning of Multiple Tasks","created":"2025-02-05","cited_by_count":14,"area":null},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2106.08453","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2308.12221","title":"Critical Learning Periods Emerge Even in Deep Linear Networks","created":"2023-08-23","cited_by_count":13,"area":null},{"id":"2202.04925","title":"Decomposing neural networks as mappings of correlation functions","created":"2022-02-10","cited_by_count":12,"area":null},{"id":"2210.04520","title":"Continual task learning in natural and artificial agents","created":"2022-10-10","cited_by_count":12,"area":null},{"id":"2210.17449","title":"Globally Gated Deep Linear Networks","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2406.03260","title":"Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers","created":"2024-06-05","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":"2105.05553","title":"Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks","created":"2021-05-12","cited_by_count":10,"area":null},{"id":"2412.11521","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","created":"2024-12-16","cited_by_count":10,"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":"2205.06910","title":"A Property Induction Framework for Neural Language Models","created":"2022-05-13","cited_by_count":9,"area":null},{"id":"2211.14961","title":"Linear Classification of Neural Manifolds with Correlated Variability","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2402.16770","title":"Neural population geometry and optimal coding of tasks with shared latent structure","created":"2024-02-26","cited_by_count":9,"area":null},{"id":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2502.21009","title":"Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2503.19859","title":"An Overview of Low-Rank Structures in the Training and Adaptation of Large Models","created":"2025-03-25","cited_by_count":9,"area":null},{"id":"2110.05960","title":"Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2208.06894","title":"The SVD of Convolutional Weights: A CNN Interpretability Framework","created":"2022-08-14","cited_by_count":8,"area":null},{"id":"2210.02996","title":"Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2502.09863","title":"Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models","created":"2025-02-14","cited_by_count":8,"area":null},{"id":"2210.17011","title":"A picture of the space of typical learnable tasks","created":"2022-10-31","cited_by_count":7,"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":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2510.12071","title":"Influence Dynamics and Stagewise Data Attribution","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2501.06141","title":"Emergent Symbol-like Number Variables in Artificial Neural Networks","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2503.02526","title":"A Theory of Initialisation's Impact on Specialisation","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2106.15456","title":"A Mechanism for Producing Aligned Latent Spaces with Autoencoders","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2209.09658","title":"Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2402.06751","title":"Low-Rank Learning by Design: the Role of Network Architecture and Activation Linearity in Gradient Rank Collapse","created":"2024-02-09","cited_by_count":5,"area":null},{"id":"2407.07279","title":"Towards a theory of learning dynamics in deep state space models","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2602.20062","title":"A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2604.07569","title":"Learning is Forgetting: LLM Training As Lossy Compression","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2209.10634","title":"Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation","created":"2022-09-21","cited_by_count":4,"area":null},{"id":"2310.19919","title":"Meta-Learning Strategies through Value Maximization in Neural Networks","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2407.20724","title":"Exploring Loss Landscapes through the Lens of Spin Glass Theory","created":"2024-07-30","cited_by_count":4,"area":null},{"id":"2505.21722","title":"Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2510.09816","title":"A mathematical theory for understanding when abstract representations emerge in neural networks","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2607.26654","title":"Constitutional Midtraining: Content Presence Drives Alignment Gains","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2106.02220","title":"Fluctuation-dissipation Type Theorem in Stochastic Linear Learning","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2206.00823","title":"Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules","created":"2022-06-02","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":"2407.09845","title":"Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks","created":"2024-07-13","cited_by_count":3,"area":null},{"id":"2411.15267","title":"Proportional infinite-width infinite-depth limit for deep linear neural networks","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2507.12553","title":"Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2508.11017","title":"Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2603.28764","title":"Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2110.02863","title":"Exploring the Common Principal Subspace of Deep Features in Neural Networks","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2209.00873","title":"Three Learning Stages and Accuracy-Efficiency Tradeoff of Restricted Boltzmann Machines","created":"2022-09-02","cited_by_count":2,"area":null},{"id":"2302.11351","title":"Abrupt and spontaneous strategy switches emerge in simple regularised neural networks","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2310.01807","title":"Discrete, compositional, and symbolic representations through attractor dynamics","created":"2023-10-03","cited_by_count":2,"area":null},{"id":"2406.03947","title":"Weight-based Decomposition: A Case for Bilinear MLPs","created":"2024-06-06","cited_by_count":2,"area":null}],"next_cursor":"100"}