{"total":56,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"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":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136,"area":null},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120,"area":null},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62,"area":"mechinterp"},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58,"area":null},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44,"area":null},{"id":"2310.05719","title":"Transformer Fusion with Optimal Transport","created":"2023-10-09","cited_by_count":36,"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":"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":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23,"area":null},{"id":"2306.10460","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","created":"2023-06-18","cited_by_count":20,"area":null},{"id":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2409.18314","title":"Realistic Evaluation of Model Merging for Compositional Generalization","created":"2024-09-26","cited_by_count":12,"area":null},{"id":"2505.23681","title":"Understanding Mode Connectivity via Parameter Space Symmetry","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2410.05583","title":"NegMerge: Sign-Consensual Weight Merging for Machine Unlearning","created":"2024-10-08","cited_by_count":9,"area":"safety"},{"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":"2312.09832","title":"Disentangling Linear Mode-Connectivity","created":"2023-12-15","cited_by_count":8,"area":null},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","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":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","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":"2403.07968","title":"Do Deep Neural Network Solutions Form a Star Domain?","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2402.05966","title":"Vanishing Feature: Diagnosing Model Merging and Beyond","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2402.03187","title":"How Good is a Single Basin?","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2502.12608","title":"Unveiling Mode Connectivity in Graph Neural Networks","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2505.02604","title":"Connecting Independently Trained Modes via Layer-Wise Connectivity","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","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":"2306.10466","title":"Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication","created":"2023-06-18","cited_by_count":2,"area":null},{"id":"2408.14677","title":"Can Optimization Trajectories Explain Multi-Task Transfer?","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2503.06001","title":"Analyzing the Role of Permutation Invariance in Linear Mode Connectivity","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2512.06297","title":"Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2305.13536","title":"Subspace-Configurable Networks","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2405.15895","title":"Manifold Metric: A Loss Landscape Approach for Predicting Model Performance","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2407.13420","title":"Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2602.17632","title":"SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"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":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.13934","title":"Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry","created":"2026-06-11","cited_by_count":0,"area":null}],"next_cursor":null}