{"total":29,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252,"area":null},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"area":null},{"id":"2505.06977","title":"CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging","created":"2025-05-11","cited_by_count":23,"area":null},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2308.13537","title":"STEM: Unleashing the Power of Embeddings for Multi-task Recommendation","created":"2023-08-16","cited_by_count":19,"area":null},{"id":"2403.00793","title":"Ads Recommendation in a Collapsed and Entangled World","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2501.15065","title":"Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts","created":"2025-01-25","cited_by_count":13,"area":null},{"id":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2501.15556","title":"Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2311.12048","title":"One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning","created":"2023-11-18","cited_by_count":8,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2408.02691","title":"Symmetric Graph Contrastive Learning against Noisy Views for Recommendation","created":"2024-08-03","cited_by_count":7,"area":null},{"id":"2509.01548","title":"Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing","created":"2025-09-01","cited_by_count":6,"area":null},{"id":"2407.14242","title":"Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2305.19844","title":"Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2510.18407","title":"Heterogeneous Adversarial Play in Interactive Environments","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2311.04698","title":"Examining Common Paradigms in Multi-Task Learning","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2410.05806","title":"A Parameter Update Balancing Algorithm for Multi-task Ranking Models in Recommendation Systems","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2510.18258","title":"NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2509.16959","title":"Graph Coloring for Multi-Task Learning","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2508.09636","title":"Personalized Product Search Ranking: A Multi-Task Learning Approach with Tabular and Non-Tabular Data","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2512.24708","title":"BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2601.15643","title":"Evolving Without Ending: Unifying Multimodal Incremental Learning for Continual Panoptic Perception","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2604.25834","title":"Action-Aware Generative Sequence Modeling for Short Video Recommendation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.12685","title":"A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.03904","title":"MAdam: Metric-Aware Multi-Objective Adam","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.16261","title":"Reducing Per-Sample Interference in Stochastic Optimization","created":"2026-06-28","cited_by_count":0,"area":null}],"next_cursor":null}