{"total":72,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2306.04226","title":"Normalization Layers Are All That Sharpness-Aware Minimization Needs","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"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":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21,"area":null},{"id":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20,"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":"2305.15817","title":"Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term","created":"2023-05-25","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":"2301.06308","title":"Stability Analysis of Sharpness-Aware Minimization","created":"2023-01-16","cited_by_count":14,"area":null},{"id":"2306.05651","title":"Differentially Private Sharpness-Aware Training","created":"2023-06-09","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":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","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":"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":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","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":"2310.03646","title":"TRAM: Bridging Trust Regions and Sharpness Aware Minimization","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2402.11262","title":"Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima","created":"2024-02-17","cited_by_count":6,"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":"2411.06710","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","created":"2024-11-11","cited_by_count":5,"area":null},{"id":"2304.04726","title":"Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging","created":"2023-04-10","cited_by_count":4,"area":null},{"id":"2309.06337","title":"Exploring Flat Minima for Domain Generalization with Large Learning Rates","created":"2023-09-12","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":"2306.07052","title":"Gradient Ascent Post-training Enhances Language Model Generalization","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2407.12996","title":"Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance","created":"2024-07-17","cited_by_count":3,"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":"2304.02688","title":"Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability","created":"2023-04-05","cited_by_count":2,"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":"2307.02337","title":"FAM: Relative Flatness Aware Minimization","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2412.18790","title":"Torque-Aware Momentum","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2505.23866","title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","created":"2025-05-29","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":"2604.19740","title":"Generalization at the Edge of Stability","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2309.13575","title":"Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantization","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2401.09622","title":"Is Hyper-Parameter Optimization Different for Software Analytics?","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2405.12489","title":"Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2406.05666","title":"Probability Distribution Learning and Its Application in Deep Learning","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2501.11584","title":"GCSAM: Gradient Centralized Sharpness Aware Minimization","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2505.24592","title":"A Flat Minima Perspective on Understanding Augmentations and Model Robustness","created":"2025-05-30","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":"2605.05769","title":"Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2302.09376","title":"Why is parameter averaging beneficial in SGD? An objective smoothing perspective","created":"2023-02-18","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":"2310.19351","title":"Seeking Flat Minima with Mean Teacher on Semi- and Weakly-Supervised Domain Generalization for Object Detection","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2403.00574","title":"Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2404.15928","title":"Generalization Measures for Zero-Shot Cross-Lingual Transfer","created":"2024-04-24","cited_by_count":0,"area":null},{"id":"2410.14375","title":"Causal Fine-Tuning under Latent Confounded Shift","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2508.09418","title":"Domain-Generalization to Improve Learning in Meta-Learning Algorithms","created":"2025-08-13","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":"2510.12451","title":"A Function-Centric Perspective on Flat and Sharp Minima","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.18812","title":"A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.12695","title":"A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2601.10251","title":"X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.23131","title":"Regularisation in neural networks: a survey and empirical analysis of approaches","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.21372","title":"The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2606.01521","title":"Fast Generalization after Interpolation via Critically Damped Momentum Optimization","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.28304","title":"Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}