{"total":82,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"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":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"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":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2207.06543","title":"CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One","created":"2022-07-13","cited_by_count":43,"area":null},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"area":null},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2110.07905","title":"Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector","created":"2021-10-15","cited_by_count":34,"area":null},{"id":"2210.09759","title":"Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models","created":"2022-10-18","cited_by_count":29,"area":null},{"id":"2211.10445","title":"Building a Subspace of Policies for Scalable Continual Learning","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2307.06966","title":"Layer-wise Linear Mode Connectivity","created":"2023-07-13","cited_by_count":22,"area":null},{"id":"2302.14685","title":"DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks","created":"2023-02-28","cited_by_count":20,"area":null},{"id":"2210.11948","title":"lo-fi: distributed fine-tuning without communication","created":"2022-10-19","cited_by_count":19,"area":null},{"id":"2202.09826","title":"Continual Learning Beyond a Single Model","created":"2022-02-20","cited_by_count":18,"area":null},{"id":"2110.05169","title":"Learning a subspace of policies for online adaptation in Reinforcement Learning","created":"2021-10-11","cited_by_count":14,"area":null},{"id":"2306.16817","title":"Improving Online Continual Learning Performance and Stability with Temporal Ensembles","created":"2023-06-29","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":"2109.07628","title":"Connecting Low-Loss Subspace for Personalized Federated Learning","created":"2021-09-16","cited_by_count":12,"area":null},{"id":"2311.00919","title":"MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training","created":"2023-11-02","cited_by_count":12,"area":"safety"},{"id":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2310.14227","title":"Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective","created":"2023-10-22","cited_by_count":10,"area":null},{"id":"2404.06498","title":"Simultaneous linear connectivity of neural networks modulo permutation","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2506.13234","title":"The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2411.02207","title":"Collective Model Intelligence Requires Compatible Specialization","created":"2024-11-04","cited_by_count":7,"area":null},{"id":"2205.15322","title":"Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training","created":"2022-05-30","cited_by_count":6,"area":null},{"id":"2206.15047","title":"Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation","created":"2022-06-30","cited_by_count":6,"area":"distill"},{"id":"2205.07315","title":"Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2410.23660","title":"Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2501.15718","title":"CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling","created":"2025-01-27","cited_by_count":5,"area":null},{"id":"2601.05052","title":"DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights","created":"2026-01-08","cited_by_count":5,"area":"diffusion"},{"id":"2203.03692","title":"Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks","created":"2022-03-07","cited_by_count":4,"area":"safety"},{"id":"2304.13718","title":"Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2402.03187","title":"How Good is a Single Basin?","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2110.04252","title":"LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2205.09891","title":"Interpolating Compressed Parameter Subspaces","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2306.12691","title":"Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems","created":"2023-06-22","cited_by_count":3,"area":null},{"id":"2401.12950","title":"Bayesian Semi-structured Subspace Inference","created":"2024-01-23","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":"2407.03641","title":"Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2412.17023","title":"Parameter-Efficient Interventions for Enhanced Model Merging","created":"2024-12-22","cited_by_count":3,"area":null},{"id":"2209.14996","title":"Multiple Modes for Continual Learning","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2211.10882","title":"Multi-head Ensemble of Smoothed Classifiers for Certified Robustness","created":"2022-11-20","cited_by_count":2,"area":null},{"id":"2305.14122","title":"Transferring Learning Trajectories of Neural Networks","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2305.14852","title":"Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2306.11304","title":"Traversing Between Modes in Function Space for Fast Ensembling","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2310.15793","title":"Improving generalization in large language models by learning prefix subspaces","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2412.14865","title":"Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning","created":"2024-12-19","cited_by_count":2,"area":"offlinerl"},{"id":"2504.08554","title":"Boosting-inspired online learning with transfer for railway maintenance","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2506.02883","title":"A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks","created":"2025-06-03","cited_by_count":2,"area":"offlinerl"},{"id":"2506.07467","title":"Circumventing Backdoor Space via Weight Symmetry","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2207.10237","title":"SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks","created":"2022-07-21","cited_by_count":1,"area":null},{"id":"2302.10279","title":"Image Reconstruction via Deep Image Prior Subspaces","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2308.08688","title":"Lightweight Adaptation of Neural Language Models via Subspace Embedding","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2411.06770","title":"Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2502.15940","title":"Orthogonal Calibration for Asynchronous Federated Learning","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2510.14845","title":"Backdoor Unlearning by Linear Task Decomposition","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2602.09689","title":"Model soups need only one ingredient","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2207.03804","title":"On the Subspace Structure of Gradient-Based Meta-Learning","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2305.13536","title":"Subspace-Configurable Networks","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2402.18949","title":"FedGuCci: Making Local Models More Connected in Landscape for Federated Learning","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2410.12927","title":"Deep Model Merging: The Sister of Neural Network Interpretability -- A Survey","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2503.07066","title":"You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time","created":"2025-03-10","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":"2512.12744","title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2512.20291","title":"Mixture-of-Experts with Gradient Conflict-Driven Subspace Topology Pruning for Emergent Modularity","created":"2025-12-23","cited_by_count":0,"area":"moe"},{"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":"2606.25087","title":"Neural Network Quantization by Learning Low-Loss Subspaces","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.19539","title":"Compressed Active Subspaces for Scalable Bayesian Inference","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20267","title":"CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models","created":"2026-07-29","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}