{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2501.00656","title":"2 OLMo 2 Furious","created":"2024-12-31","cited_by_count":340},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"2301.11235","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","created":"2023-01-26","cited_by_count":163},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137},{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123},{"id":"2002.06716","title":"Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data","created":"2020-02-17","cited_by_count":115},{"id":"2509.02046","title":"Fantastic Pretraining Optimizers and Where to Find Them","created":"2025-09-02","cited_by_count":100},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86},{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78},{"id":"2410.21265","title":"Modular Duality in Deep Learning","created":"2024-10-28","cited_by_count":77},{"id":"2509.01440","title":"Benchmarking Optimizers for Large Language Model Pretraining","created":"2025-09-01","cited_by_count":68},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64},{"id":"2006.09313","title":"Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks","created":"2020-06-16","cited_by_count":62},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47},{"id":"2509.26030","title":"Muon Outperforms Adam in Tail-End Associative Memory Learning","created":"2025-09-30","cited_by_count":46},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31},{"id":"2512.04299","title":"When do spectral gradient updates help in deep learning?","created":"2025-12-03","cited_by_count":31},{"id":"2211.06506","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","created":"2022-11-11","cited_by_count":30},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30},{"id":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27},{"id":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20},{"id":"2509.24882","title":"Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime","created":"2025-09-29","cited_by_count":20},{"id":"2410.18938","title":"A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities","created":"2024-10-24","cited_by_count":16},{"id":"2506.14562","title":"AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs","created":"2025-06-17","cited_by_count":13},{"id":"2406.03068","title":"Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers","created":"2024-06-05","cited_by_count":12},{"id":"2506.00772","title":"LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning","created":"2025-06-01","cited_by_count":12},{"id":"2507.17912","title":"SETOL: A Semi-Empirical Theory of (Deep) Learning","created":"2025-07-23","cited_by_count":12},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11},{"id":"2506.03470","title":"Models of Heavy-Tailed Mechanistic Universality","created":"2025-06-04","cited_by_count":10},{"id":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","cited_by_count":10},{"id":"2406.04657","title":"From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks","created":"2024-06-07","cited_by_count":9},{"id":"2602.04669","title":"Delving into Muon and Beyond: Deep Analysis and Extensions","created":"2026-02-04","cited_by_count":9},{"id":"2601.11789","title":"Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis","created":"2026-01-16","cited_by_count":5}],"next_cursor":null}