{"total":15,"rows":[{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2506.22712","title":"Generalized Linear Mode Connectivity for Transformers","created":"2025-06-28","cited_by_count":16,"area":null},{"id":"2410.05357","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2501.00061","title":"Training-free Heterogeneous Model Merging","created":"2024-12-29","cited_by_count":6,"area":null},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2506.11403","title":"A correlation-permutation approach for speech-music encoders model merging","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2606.23607","title":"Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2501.06126","title":"Merging Feed-Forward Sublayers for Compressed Transformers","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2507.04517","title":"DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2501.14846","title":"Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval","created":"2025-01-24","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},{"id":"2606.04754","title":"Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability","created":"2026-06-03","cited_by_count":0,"area":null}],"next_cursor":null}