{"total":95,"rows":[{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"area":"ssm"},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92,"area":null},{"id":"2502.05374","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","created":"2025-02-07","cited_by_count":79,"area":"safety"},{"id":"2306.06189","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","created":"2023-06-09","cited_by_count":65,"area":null},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43,"area":null},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41,"area":"ssm"},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","cited_by_count":37,"area":null},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2303.13087","title":"Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization","created":"2023-03-23","cited_by_count":29,"area":null},{"id":"2407.18559","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","created":"2024-07-26","cited_by_count":29,"area":"ssm"},{"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":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2310.16412","title":"FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17,"area":null},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"area":"ssm"},{"id":"2209.08473","title":"Bootstrap Generalization Ability from Loss Landscape Perspective","created":"2022-09-18","cited_by_count":16,"area":null},{"id":"2504.14662","title":"Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning","created":"2025-04-20","cited_by_count":16,"area":null},{"id":"2306.05651","title":"Differentially Private Sharpness-Aware Training","created":"2023-06-09","cited_by_count":14,"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":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2305.10769","title":"Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2404.00357","title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","created":"2024-03-30","cited_by_count":13,"area":null},{"id":"2401.10809","title":"Neglected Hessian component explains mysteries in Sharpness regularization","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2405.18861","title":"Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2601.17237","title":"C-RADIOv4 (Tech Report)","created":"2026-01-24","cited_by_count":12,"area":null},{"id":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","cited_by_count":10,"area":null},{"id":"2302.09693","title":"mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization","created":"2023-02-19","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2412.13573","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2402.09240","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","created":"2024-02-14","cited_by_count":9,"area":null},{"id":"2405.20439","title":"Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2211.11489","title":"Efficient Generalization Improvement Guided by Random Weight Perturbation","created":"2022-11-21","cited_by_count":8,"area":null},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8,"area":null},{"id":"2410.10683","title":"SAMPa: Sharpness-aware Minimization Parallelized","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2412.03752","title":"Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning","created":"2024-12-04","cited_by_count":8,"area":null},{"id":"2503.08140","title":"HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views","created":"2025-03-11","cited_by_count":8,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2404.11769","title":"QGen: On the Ability to Generalize in Quantization Aware Training","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2406.13137","title":"Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2510.08625","title":"Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models","created":"2025-10-08","cited_by_count":7,"area":"diffusion"},{"id":"2210.13533","title":"Sufficient Invariant Learning for Distribution Shift","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2302.05629","title":"Improving Differentiable Architecture Search via Self-Distillation","created":"2023-02-11","cited_by_count":6,"area":"distill"},{"id":"2310.03646","title":"TRAM: Bridging Trust Regions and Sharpness Aware Minimization","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2410.22656","title":"Tilted Sharpness-Aware Minimization","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2506.05454","title":"Zeroth-Order Optimization Finds Flat Minima","created":"2025-06-05","cited_by_count":6,"area":"deeprl"},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2212.04343","title":"Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2302.11836","title":"On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2306.04178","title":"Optimal Transport Model Distributional Robustness","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2307.16704","title":"Lookbehind-SAM: k steps back, 1 step forward","created":"2023-07-31","cited_by_count":5,"area":null},{"id":"2311.06423","title":"Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2406.08001","title":"Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2410.16845","title":"Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2511.03548","title":"Flat Minima and Generalization: Insights from Stochastic Convex Optimization","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2505.24399","title":"LightSAM: Parameter-Agnostic Sharpness-Aware Minimization","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.12409","title":"Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models","created":"2025-06-14","cited_by_count":3,"area":"mllm"},{"id":"2508.19564","title":"Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2511.09170","title":"HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2306.09121","title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2310.00488","title":"Membership Privacy Risks of Sharpness Aware Minimization","created":"2023-09-30","cited_by_count":2,"area":null},{"id":"2406.07107","title":"Agnostic Sharpness-Aware Minimization","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2409.13173","title":"Bilateral Sharpness-Aware Minimization for Flatter Minima","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2411.12352","title":"Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training","created":"2024-11-19","cited_by_count":2,"area":null},{"id":"2509.18001","title":"Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2605.21308","title":"Deformba: Vision State Space Model with Adaptive State Fusion","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2305.10252","title":"Sharpness & Shift-Aware Self-Supervised Learning","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2308.13541","title":"Adversarial Collaborative Filtering for Free","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2403.08821","title":"Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2403.09086","title":"Learning from straggler clients in federated learning","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2503.24057","title":"AMMSM: Adaptive Motion Magnification and Sparse Mamba for Micro-Expression Recognition","created":"2025-03-31","cited_by_count":1,"area":"ssm"},{"id":"2508.18860","title":"C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.02433","title":"VASSO: Variance Suppression for Sharpness-Aware Minimization","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.07758","title":"R\\'enyi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2604.11064","title":"A Faster Path to Continual Learning","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2211.00310","title":"SADT: Combining Sharpness-Aware Minimization with Self-Distillation for Improved Model Generalization","created":"2022-11-01","cited_by_count":0,"area":"distill"},{"id":"2211.11561","title":"SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness","created":"2022-11-18","cited_by_count":0,"area":null},{"id":"2304.14224","title":"Self-discipline on multiple channels","created":"2023-04-27","cited_by_count":0,"area":"distill"},{"id":"2305.04526","title":"CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation","created":"2023-05-08","cited_by_count":0,"area":null},{"id":"2305.15536","title":"RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2307.09638","title":"Promoting Exploration in Memory-Augmented Adam using Critical Momenta","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2309.17215","title":"Sharpness-Aware Teleportation on Riemannian Manifolds","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2405.13961","title":"SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data","created":"2024-05-22","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":"2510.02174","title":"Flatness-Aware Stochastic Gradient Langevin Dynamics","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.03763","title":"Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2512.07884","title":"GSPN-2: Efficient Parallel Sequence Modeling","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2609.33325","title":"VisionHOPE: Visual Backbones as Self-Modifying Learning Systems","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}