{"total":14,"rows":[{"id":"2605.10661","title":"Investigating Single-Block Recurrence in Vision Transformers for Image Recognition","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2606.17830","title":"Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2510.04686","title":"How does the optimizer implicitly bias the model merging loss landscape?","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.19155","title":"VeFA: Vector-Based Feature Space Adaptation for Robust Model Fine-Tuning","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2604.02719","title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","created":"2026-04-03","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":"2605.22350","title":"Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2607.19971","title":"Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2604.13658","title":"Post-Hoc Uncertainty-Aware Explanations for Deployed Power Quality Disturbance Classifiers via Laplace Approximation","created":"2026-04-15","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},{"id":"2608.28840","title":"Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.26147","title":"Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM Families","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2610.18471","title":"Graph Metanetworks for Transformer Based Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}