{"total":48,"rows":[{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252,"area":null},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"area":null},{"id":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104,"area":null},{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2406.18533","title":"On Scaling Up 3D Gaussian Splatting Training","created":"2024-06-26","cited_by_count":49,"area":null},{"id":"2507.07101","title":"Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful","created":"2025-07-09","cited_by_count":41,"area":null},{"id":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2412.01505","title":"Scaling Law for Language Models Training Considering Batch Size","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2109.09304","title":"Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks","created":"2021-09-20","cited_by_count":21,"area":null},{"id":"2106.03696","title":"Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2410.18565","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","cited_by_count":13,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2306.07850","title":"Exact Mean Square Linear Stability Analysis for SGD","created":"2023-06-13","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2604.14108","title":"Momentum Further Constrains Sharpness at the Edge of Stochastic Stability","created":"2026-04-15","cited_by_count":10,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2402.11215","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","created":"2024-02-17","cited_by_count":8,"area":null},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2311.10517","title":"Mind the map! Accounting for existing map information when estimating online HDMaps from sensor","created":"2023-11-17","cited_by_count":6,"area":null},{"id":"2409.12371","title":"Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularization","created":"2024-09-19","cited_by_count":6,"area":null},{"id":"2510.14717","title":"Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2309.14053","title":"Revisiting LARS for Large Batch Training Generalization of Neural Networks","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2402.18824","title":"Batch size invariant Adam","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2504.15208","title":"Compute-Optimal LLMs Provably Generalize Better With Scale","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2205.08601","title":"Universal characteristics of deep neural network loss surfaces from random matrix theory","created":"2022-05-17","cited_by_count":4,"area":null},{"id":"2307.11948","title":"The instabilities of large learning rate training: a loss landscape view","created":"2023-07-22","cited_by_count":3,"area":null},{"id":"2602.14789","title":"On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2606.28486","title":"Spectral phase transitions and trainability in neural network learning dynamics","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2407.20650","title":"No learning rates needed: Introducing SALSA -- Stable Armijo Line Search Adaptation","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2412.11739","title":"Asymmetric Learning for Spectral Graph Neural Networks","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2509.01349","title":"Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2509.21614","title":"Effective continuous equations for adaptive SGD: a stochastic analysis view","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2602.00816","title":"Hessian Spectral Analysis at Foundation Model Scale","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.29108","title":"Efficient Bilevel Optimization with KFAC-Based Hypergradients","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2305.18490","title":"SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2305.18864","title":"Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2306.10959","title":"RaViTT: Random Vision Transformer Tokens","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2406.03696","title":"Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2411.02908","title":"Photon: Federated LLM Pre-Training","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2412.17613","title":"Can Stability be Detrimental? Better Generalization through Gradient Descent Instabilities","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2505.09796","title":"Virtual Dosimetrists: A Radiotherapy Training \"Flight Simulator\"","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2510.17120","title":"Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2604.14669","title":"Zeroth-Order Optimization at the Edge of Stability","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.06835","title":"On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}