{"total":82,"rows":[{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"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,"area":"moe"},{"id":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123,"area":null},{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109,"area":"agents"},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102,"area":"moe"},{"id":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94,"area":null},{"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,"area":null},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2408.04693","title":"Understanding the Performance and Estimating the Cost of LLM Fine-Tuning","created":"2024-08-08","cited_by_count":48,"area":"moe"},{"id":"2406.13233","title":"AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models","created":"2024-06-19","cited_by_count":44,"area":"moe"},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35,"area":"moe"},{"id":"2508.07981","title":"Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation","created":"2025-08-11","cited_by_count":27,"area":null},{"id":"2510.13003","title":"OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning","created":"2025-10-14","cited_by_count":21,"area":null},{"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,"area":"moe"},{"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":"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":"2509.25684","title":"LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts","created":"2025-09-30","cited_by_count":13,"area":"moe"},{"id":"2407.04938","title":"SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation","created":"2024-07-06","cited_by_count":12,"area":"moe"},{"id":"2503.06881","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","created":"2025-03-10","cited_by_count":12,"area":"moe"},{"id":"2505.22582","title":"Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts","created":"2025-05-28","cited_by_count":12,"area":"moe"},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"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,"area":"moe"},{"id":"2509.21892","title":"Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts","created":"2025-09-26","cited_by_count":11,"area":"moe"},{"id":"2405.00557","title":"Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment","created":"2024-05-01","cited_by_count":10,"area":"lr"},{"id":"2408.09856","title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2411.08212","title":"PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model","created":"2024-11-12","cited_by_count":9,"area":"moe"},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2407.21571","title":"PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning","created":"2024-07-31","cited_by_count":8,"area":"moe"},{"id":"2412.08587","title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","created":"2024-12-11","cited_by_count":7,"area":null},{"id":"2409.13202","title":"CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance","created":"2024-09-20","cited_by_count":6,"area":"agents"},{"id":"2410.01610","title":"Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging","created":"2024-10-02","cited_by_count":6,"area":"moe"},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2506.05191","title":"MokA: Multimodal Low-Rank Adaptation for MLLMs","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2601.07935","title":"Towards Specialized Generalists: A Multi-Task MoE-LoRA Framework for Domain-Specific LLM Adaptation","created":"2026-01-12","cited_by_count":6,"area":"moe"},{"id":"2602.07011","title":"MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2506.14436","title":"MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation","created":"2025-06-17","cited_by_count":5,"area":"moe"},{"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,"area":"moe"},{"id":"2406.14434","title":"Selected Languages are All You Need for Cross-lingual Truthfulness Transfer","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2412.08946","title":"MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learning","created":"2024-12-12","cited_by_count":4,"area":"moe"},{"id":"2505.17553","title":"CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning","created":"2025-05-23","cited_by_count":4,"area":"moe"},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2510.04136","title":"MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition","created":"2025-10-05","cited_by_count":4,"area":"moe"},{"id":"2603.00573","title":"CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging","created":"2026-02-28","cited_by_count":4,"area":"moe"},{"id":"2503.00245","title":"CoSMoEs: Compact Sparse Mixture of Experts","created":"2025-02-28","cited_by_count":3,"area":"moe"},{"id":"2506.00495","title":"FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.05928","title":"MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":3,"area":"moe"},{"id":"2509.07945","title":"One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning","created":"2025-09-09","cited_by_count":3,"area":"wm"},{"id":"2509.25414","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2601.22828","title":"Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA","created":"2026-01-30","cited_by_count":3,"area":"mllm"},{"id":"2607.05114","title":"Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing","created":"2026-07-06","cited_by_count":3,"area":"moe"},{"id":"2410.21705","title":"AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discovery","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2506.11999","title":"Generative Representational Learning of Foundation Models for Recommendation","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2512.11366","title":"qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2601.22708","title":"A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation","created":"2026-01-30","cited_by_count":2,"area":null},{"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,"area":"moe"},{"id":"2603.27481","title":"On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models","created":"2026-03-29","cited_by_count":2,"area":"mllm"},{"id":"2605.20247","title":"CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning","created":"2026-05-18","cited_by_count":2,"area":"moe"},{"id":"2608.09251","title":"MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts","created":"2026-08-10","cited_by_count":2,"area":"agents"},{"id":"2406.11354","title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2504.06803","title":"DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation","created":"2025-04-09","cited_by_count":1,"area":"diffusion"},{"id":"2506.00236","title":"Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2604.01152","title":"Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning","created":"2026-04-01","cited_by_count":1,"area":"moe"},{"id":"2604.01310","title":"Sparse Spectral LoRA: Routed Experts for Medical VLMs","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2604.26340","title":"Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning","created":"2026-04-29","cited_by_count":1,"area":"moe"},{"id":"2605.07562","title":"Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2605.28084","title":"SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2607.07023","title":"Online Data Selection Is Implicit Alignment","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2410.03137","title":"SAG: Style-Aligned Article Generation via Model Collaboration","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2412.17383","title":"Interweaving Memories of a Siamese Large Language Model","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2509.14269","title":"SparseDoctor: Towards Efficient Chat Doctor with Mixture of Experts Enhanced Large Language Models","created":"2025-09-15","cited_by_count":0,"area":"moe"},{"id":"2512.07309","title":"Radiance-Field Guided Pretraining: Scaling Localization Models with Unlabeled Wireless Signals","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2604.12526","title":"Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA","created":"2026-04-14","cited_by_count":0,"area":"safety"},{"id":"2606.19346","title":"Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2608.02129","title":"PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.00242","title":"CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction","created":"2026-08-31","cited_by_count":0,"area":"driving"},{"id":"2609.18842","title":"Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.32002","title":"What Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.02126","title":"Local Support Learning","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}