{"list":"other","total":59,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147},{"id":"2008.09036","title":"Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries","created":"2020-08-20","cited_by_count":107},{"id":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94},{"id":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65},{"id":"2410.13025","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","created":"2024-10-16","cited_by_count":52},{"id":"2402.07148","title":"X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design","created":"2024-02-11","cited_by_count":42},{"id":"1802.10542","title":"Memory-based Parameter Adaptation","created":"2018-02-28","cited_by_count":35},{"id":"2211.03831","title":"Multi-Head Adapter Routing for Cross-Task Generalization","created":"2022-11-07","cited_by_count":33},{"id":"2508.01832","title":"MLP Memory: A Retriever-Pretrained Memory for Large Language Models","created":"2025-08-03","cited_by_count":20},{"id":"2505.22934","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","created":"2025-05-28","cited_by_count":19},{"id":"2405.17741","title":"LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design","created":"2024-05-28","cited_by_count":18},{"id":"2406.12824","title":"From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries","created":"2024-06-18","cited_by_count":16},{"id":"2508.09874","title":"Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models","created":"2025-08-13","cited_by_count":16},{"id":"2603.21389","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","created":"2026-03-22","cited_by_count":15},{"id":"2406.16989","title":"Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning","created":"2024-06-24","cited_by_count":14},{"id":"2509.25684","title":"LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts","created":"2025-09-30","cited_by_count":13},{"id":"2406.09679","title":"Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters","created":"2024-06-14","cited_by_count":12},{"id":"2408.09053","title":"Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models","created":"2024-08-16","cited_by_count":11},{"id":"2504.00661","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","created":"2025-04-01","cited_by_count":11},{"id":"2508.05232","title":"Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs","created":"2025-08-07","cited_by_count":10},{"id":"2509.26614","title":"Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification","created":"2025-09-30","cited_by_count":10},{"id":"2405.19010","title":"Evaluating the External and Parametric Knowledge Fusion of Large Language Models","created":"2024-05-29","cited_by_count":9},{"id":"2507.05346","title":"LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks","created":"2025-07-07","cited_by_count":8},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7},{"id":"2604.04503","title":"Memory Intelligence Agent","created":"2026-04-06","cited_by_count":7},{"id":"2504.03454","title":"SpectR: Dynamically Composing LM Experts with Spectral Routing","created":"2025-04-04","cited_by_count":6},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6},{"id":"2506.21035","title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","created":"2025-06-26","cited_by_count":5},{"id":"2508.02107","title":"AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation","created":"2025-08-04","cited_by_count":5},{"id":"2604.05966","title":"FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures","created":"2026-04-07","cited_by_count":5},{"id":"2604.27974","title":"FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting","created":"2026-04-30","cited_by_count":5},{"id":"2605.19320","title":"TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards","created":"2026-05-19","cited_by_count":5},{"id":"2510.12266","title":"HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization","created":"2025-10-14","cited_by_count":4},{"id":"2603.00573","title":"CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging","created":"2026-02-28","cited_by_count":4},{"id":"2604.24023","title":"ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services","created":"2026-04-27","cited_by_count":4},{"id":"2606.09162","title":"Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation","created":"2026-06-08","cited_by_count":4},{"id":"2510.02388","title":"Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation","created":"2025-09-30","cited_by_count":3},{"id":"2406.16143","title":"Review of Zero-Shot and Few-Shot AI Algorithms in The Medical Domain","created":"2024-06-23","cited_by_count":2},{"id":"2410.01497","title":"DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models","created":"2024-10-02","cited_by_count":2},{"id":"2410.09908","title":"Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection","created":"2024-10-13","cited_by_count":2},{"id":"2512.11366","title":"qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs","created":"2025-12-12","cited_by_count":2},{"id":"2603.11873","title":"AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization","created":"2026-03-12","cited_by_count":2},{"id":"2603.26299","title":"Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy","created":"2026-03-27","cited_by_count":2},{"id":"2606.31045","title":"LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents","created":"2026-06-30","cited_by_count":2},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1},{"id":"2508.03999","title":"Tensorized Clustered LoRA Merging for Multi-Task Interference","created":"2025-08-06","cited_by_count":1},{"id":"2509.18093","title":"SEQR: Secure and Efficient QR-based LoRA Routing","created":"2025-09-22","cited_by_count":1},{"id":"2601.12990","title":"Beyond Visual Realism: Toward Reliable Financial Time Series Generation","created":"2026-01-19","cited_by_count":1},{"id":"2602.08369","title":"MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval","created":"2026-02-09","cited_by_count":1}],"next_cursor":null}