{"total":59,"rows":[{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2509.10377","title":"Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs","created":"2025-09-12","cited_by_count":25,"area":"moe"},{"id":"2505.22934","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","created":"2025-05-28","cited_by_count":19,"area":null},{"id":"2505.15875","title":"Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging","created":"2025-05-21","cited_by_count":18,"area":null},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"id":"2410.13910","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2505.11883","title":"MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging","created":"2025-05-17","cited_by_count":14,"area":null},{"id":"2501.15103","title":"Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning","created":"2025-01-25","cited_by_count":13,"area":"moe"},{"id":"2512.23017","title":"Merge before Forget: A Single LoRA Continual Learning via Continual Merging","created":"2025-12-28","cited_by_count":11,"area":null},{"id":"2502.12988","title":"Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2505.20525","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2506.05713","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2510.12266","title":"HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2510.13537","title":"K-Merge: Online Continual Merging of Adapters for On-device Large Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2601.09473","title":"SimMerge: Learning to Select Merge Operators from Similarity Signals","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2603.26317","title":"Label-Free Cross-Task LoRA Merging with Null-Space Compression","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2505.18867","title":"Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2505.22602","title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2510.14163","title":"Towards Reversible Model Merging For Low-rank Weights","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2606.03723","title":"Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2505.23209","title":"Navigating the Accuracy-Size Trade-Off with Flexible Model Merging","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2508.08827","title":"TiMoE: Time-Aware Mixture of Language Experts","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2512.01461","title":"Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2603.26299","title":"Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.18521","title":"Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2606.19549","title":"Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.01194","title":"FedRPCA: Enhancing Federated LoRA Aggregation Using Robust PCA","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2509.10535","title":"Semantic-guided LoRA Parameters Generation","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2605.14841","title":"GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2608.09490","title":"When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2506.13479","title":"Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2508.11985","title":"Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2508.19353","title":"Efficient Multi-Source Knowledge Transfer by Model Merging","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.12951","title":"Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2601.16097","title":"Incremental Multilingual Text2Cypher with Adapter Combination","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.03696","title":"Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.09413","title":"LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.16826","title":"Crowded in B-Space: Calibrating Shared Directions for LoRA Merging","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.12345","title":"Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.20189","title":"SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2606.19079","title":"Semantic Adapter Routing with Fine-Tuning Task Embeddings","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.30360","title":"On the Vulnerability of Parameter-Level Defenses to Model Merging","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31413","title":"Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.10985","title":"MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration","created":"2026-07-13","cited_by_count":0,"area":"mllm"},{"id":"2607.15661","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","created":"2026-07-17","cited_by_count":0,"area":"mllm"},{"id":"2607.27497","title":"SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2609.15743","title":"Merging the Knowledge of LLMs for Automatic Speech Recognition","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.22237","title":"Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.31600","title":"New LoRA Skills Should Read but Never Write","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33125","title":"Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface","created":"2026-09-27","cited_by_count":0,"area":"vla"},{"id":"2610.00431","title":"ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16664","title":"Making LoRA Identifiable: Orthogonal Alignment for Continual Learning","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}