{"total":27,"rows":[{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2405.18890","title":"Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization","created":"2024-05-29","cited_by_count":28,"area":null},{"id":"2402.15152","title":"On the Duality Between Sharpness-Aware Minimization and Adversarial Training","created":"2024-02-23","cited_by_count":24,"area":null},{"id":"2410.10373","title":"Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training","created":"2024-10-14","cited_by_count":24,"area":null},{"id":"2307.06966","title":"Layer-wise Linear Mode Connectivity","created":"2023-07-13","cited_by_count":22,"area":null},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14,"area":null},{"id":"2405.20763","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","created":"2024-05-31","cited_by_count":14,"area":null},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2506.04805","title":"Adaptive Preconditioners Trigger Loss Spikes in Adam","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2410.10683","title":"SAMPa: Sharpness-aware Minimization Parallelized","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2506.07376","title":"Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2410.22656","title":"Tilted Sharpness-Aware Minimization","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2502.03503","title":"Analyzing limits for in-context learning","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2412.05169","title":"Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2408.14677","title":"Can Optimization Trajectories Explain Multi-Task Transfer?","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2503.11147","title":"Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2511.17918","title":"Do Flat Minima Improve Sparse Novel View Synthesis?","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2406.06700","title":"Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2411.05771","title":"Equivariant Test-Time Training with Operator Sketching for Imaging Inverse Problems","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2508.10435","title":"Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.21818","title":"Sharpness-Aware Minimization Can Hallucinate Minimizers","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.00958","title":"The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2511.17399","title":"Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2607.18306","title":"Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.24173","title":"SandwichQuant: Which Parameters Matter Before and After Quantization?","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}