{"total":32,"rows":[{"id":"2404.02418","title":"Auxiliary task demands mask the capabilities of smaller language models","created":"2024-04-03","cited_by_count":54,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40,"area":null},{"id":"2505.12477","title":"Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning","created":"2025-05-18","cited_by_count":36,"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":"2410.21869","title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","created":"2024-10-29","cited_by_count":31,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"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":"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":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12,"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":"2504.13101","title":"Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research","created":"2025-04-17","cited_by_count":9,"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":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2312.10725","title":"Harnessing small projectors and multiple views for efficient vision pretraining","created":"2023-12-17","cited_by_count":5,"area":null},{"id":"2402.05013","title":"Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2401.07085","title":"Three Mechanisms of Feature Learning in a Linear Network","created":"2024-01-13","cited_by_count":4,"area":null},{"id":"2411.01767","title":"A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2411.11176","title":"Infinite Width Limits of Self Supervised Neural Networks","created":"2024-11-17","cited_by_count":4,"area":null},{"id":"2505.12576","title":"AdaDim: Dimensionality Adaptation for SSL Representational Dynamics","created":"2025-05-18","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":"2309.02011","title":"Representation Learning Dynamics of Self-Supervised Models","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2509.07289","title":"Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Space","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2310.02903","title":"FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2403.08673","title":"When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2406.06909","title":"Training Dynamics of Nonlinear Contrastive Learning Model in the High Dimensional Limit","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2410.00772","title":"On the Generalization and Causal Explanation in Self-Supervised Learning","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2411.18645","title":"Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings","created":"2024-11-26","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":"2609.05031","title":"An Analysis of Self-supervised Pre-training with Dependent Samples","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.32487","title":"Neural Dynamics as the Composition of Quantized Units","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}