{"total":102,"rows":[{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291,"area":null},{"id":"2106.07682","title":"Revisiting Model Stitching to Compare Neural Representations","created":"2021-06-14","cited_by_count":209,"area":null},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179,"area":null},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127,"area":null},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120,"area":null},{"id":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108,"area":"moe"},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2402.00433","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","created":"2024-02-01","cited_by_count":85,"area":"moe"},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2102.13042","title":"Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling","created":"2021-02-25","cited_by_count":75,"area":null},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2307.08286","title":"Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity","created":"2023-07-17","cited_by_count":50,"area":null},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35,"area":null},{"id":"2310.13397","title":"Equivariant Deep Weight Space Alignment","created":"2023-10-20","cited_by_count":35,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28,"area":null},{"id":"2210.14102","title":"Exploring Mode Connectivity for Pre-trained Language Models","created":"2022-10-25","cited_by_count":26,"area":null},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"area":null},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25,"area":null},{"id":"2403.11871","title":"The Real Tropical Geometry of Neural Networks","created":"2024-03-18","cited_by_count":24,"area":null},{"id":"2209.07509","title":"Random initialisations performing above chance and how to find them","created":"2022-09-15","cited_by_count":23,"area":null},{"id":"2304.03094","title":"PopulAtion Parameter Averaging (PAPA)","created":"2023-04-06","cited_by_count":23,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2104.05508","title":"Noether: The More Things Change, the More Stay the Same","created":"2021-04-12","cited_by_count":19,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2305.08702","title":"Recyclable Tuning for Continual Pre-training","created":"2023-05-15","cited_by_count":17,"area":null},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17,"area":null},{"id":"2505.22697","title":"Update Your Transformer to the Latest Release: Re-Basin of Task Vectors","created":"2025-05-28","cited_by_count":17,"area":null},{"id":"2403.00986","title":"Merging Text Transformer Models from Different Initializations","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2502.12420","title":"Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models","created":"2025-02-18","cited_by_count":16,"area":null},{"id":"2506.22712","title":"Generalized Linear Mode Connectivity for Transformers","created":"2025-06-28","cited_by_count":16,"area":null},{"id":"2310.18477","title":"Understanding and Improving Ensemble Adversarial Defense","created":"2023-10-27","cited_by_count":14,"area":null},{"id":"2204.10782","title":"On Feature Learning in Neural Networks with Global Convergence Guarantees","created":"2022-04-22","cited_by_count":13,"area":null},{"id":"2310.06756","title":"Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2504.10185","title":"LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks","created":"2025-04-14","cited_by_count":12,"area":"safety"},{"id":"2102.09671","title":"When Are Solutions Connected in Deep Networks?","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2309.14597","title":"Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2503.08998","title":"From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches","created":"2025-03-12","cited_by_count":11,"area":null},{"id":"2210.01019","title":"Plateau in Monotonic Linear Interpolation -- A \"Biased\" View of Loss Landscape for Deep Networks","created":"2022-10-03","cited_by_count":10,"area":null},{"id":"2505.23681","title":"Understanding Mode Connectivity via Parameter Space Symmetry","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2208.07951","title":"On the generalization of learning algorithms that do not converge","created":"2022-08-16","cited_by_count":9,"area":null},{"id":"2402.04051","title":"Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2404.06391","title":"Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity","created":"2024-04-09","cited_by_count":9,"area":null},{"id":"2407.05385","title":"Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis","created":"2024-07-07","cited_by_count":9,"area":null},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2411.00247","title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2101.08576","title":"A Note on Connectivity of Sublevel Sets in Deep Learning","created":"2021-01-21","cited_by_count":8,"area":null},{"id":"2210.12001","title":"When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2509.11348","title":"On Linear Mode Connectivity of Mixture-of-Experts Architectures","created":"2025-09-14","cited_by_count":8,"area":"moe"},{"id":"2102.13233","title":"Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations","created":"2021-02-25","cited_by_count":7,"area":null},{"id":"2210.17011","title":"A picture of the space of typical learnable tasks","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2403.02799","title":"DPPA: Pruning Method for Large Language Model to Model Merging","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2109.14142","title":"On the Provable Generalization of Recurrent Neural Networks","created":"2021-09-29","cited_by_count":6,"area":null},{"id":"2410.14837","title":"Topological obstruction to the training of shallow ReLU neural networks","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2106.04186","title":"What training reveals about neural network complexity","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2210.16400","title":"Flatter, faster: scaling momentum for optimal speedup of SGD","created":"2022-10-28","cited_by_count":5,"area":null},{"id":"2402.01514","title":"Mapping the Multiverse of Latent Representations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2309.16923","title":"Mode Connectivity and Data Heterogeneity of Federated Learning","created":"2023-09-29","cited_by_count":3,"area":null},{"id":"2403.03333","title":"Federated Learning over Connected Modes","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2404.13404","title":"Solution space and storage capacity of fully connected two-layer neural networks with generic activation functions","created":"2024-04-20","cited_by_count":3,"area":null},{"id":"2502.12608","title":"Unveiling Mode Connectivity in Graph Neural Networks","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2603.22030","title":"On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2305.14122","title":"Transferring Learning Trajectories of Neural Networks","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2310.18769","title":"Linear Mode Connectivity in Sparse Neural Networks","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2503.06001","title":"Analyzing the Role of Permutation Invariance in Linear Mode Connectivity","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.20344","title":"A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2510.08023","title":"Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2602.08564","title":"M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2111.05311","title":"Mode connectivity in the loss landscape of parameterized quantum circuits","created":"2021-11-09","cited_by_count":1,"area":null},{"id":"2204.01365","title":"Deep learning, stochastic gradient descent and diffusion maps","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2311.06816","title":"On original and latent space connectivity in deep neural networks","created":"2023-11-12","cited_by_count":1,"area":null},{"id":"2407.09251","title":"Deep Adversarial Defense Against Multilevel-Lp Attacks","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2504.05357","title":"Find A Winning Sign: Sign Is All We Need to Win the Lottery","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2506.18135","title":"SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2605.18919","title":"MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.12498","title":"From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.31963","title":"Signed-Permutation Coordinate Transport for RMSNorm Transformers","created":"2026-06-30","cited_by_count":1,"area":"mechinterp"},{"id":"2104.01730","title":"Training Deep Neural Networks via Branch-and-Bound","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2201.07934","title":"Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks","created":"2022-01-03","cited_by_count":0,"area":null},{"id":"2202.09276","title":"Geometric Regularization from Overparameterization","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2204.11017","title":"Federated Geometric Monte Carlo Clustering to Counter Non-IID Datasets","created":"2022-04-23","cited_by_count":0,"area":null},{"id":"2303.10225","title":"Bridging Models to Defend: A Population-Based Strategy for Robust Adversarial Defense","created":"2023-03-17","cited_by_count":0,"area":null},{"id":"2306.14817","title":"Black holes and the loss landscape in machine learning","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2412.15467","title":"Non-Uniform Parameter-Wise Model Merging","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2503.17905","title":"Finding Stable Subnetworks at Initialization with Dataset Distillation","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2508.06127","title":"SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2602.17596","title":"From Approximation Rates to Loss-Landscape Barrier Decay in Shallow ReLU Networks","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.03535","title":"Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.09991","title":"Optimizer-Induced Mode Connectivity: From AdamW to Muon","created":"2026-05-11","cited_by_count":0,"area":null}],"next_cursor":"100"}