{"total":147,"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":"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":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"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":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2503.08007","title":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","created":"2025-03-11","cited_by_count":27,"area":"vla"},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25,"area":null},{"id":"2410.10054","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","created":"2024-10-14","cited_by_count":20,"area":"moe"},{"id":"2410.07739","title":"SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture","created":"2024-10-10","cited_by_count":19,"area":"moe"},{"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":"2602.00994","title":"Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning","created":"2026-02-01","cited_by_count":17,"area":"lr"},{"id":"2405.13053","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","created":"2024-05-19","cited_by_count":16,"area":"moe"},{"id":"2412.04220","title":"Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts","created":"2024-12-05","cited_by_count":15,"area":"moe"},{"id":"2510.16882","title":"Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning","created":"2025-10-19","cited_by_count":15,"area":null},{"id":"2507.04631","title":"Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts","created":"2025-07-07","cited_by_count":14,"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":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2411.19128","title":"Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures","created":"2024-11-28","cited_by_count":12,"area":null},{"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":"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":"2510.10432","title":"Hierarchical LoRA MoE for Efficient CTR Model Scaling","created":"2025-10-12","cited_by_count":10,"area":"moe"},{"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":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2502.15828","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","created":"2025-02-20","cited_by_count":9,"area":"moe"},{"id":"2503.07416","title":"TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision","created":"2025-03-10","cited_by_count":9,"area":"diffusion"},{"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":"2505.22694","title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2509.03934","title":"SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment","created":"2025-09-04","cited_by_count":9,"area":"rag"},{"id":"2412.02205","title":"DataLab: A Unified Platform for LLM-Powered Business Intelligence","created":"2024-12-03","cited_by_count":8,"area":null},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2508.02587","title":"Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules","created":"2025-08-04","cited_by_count":8,"area":"moe"},{"id":"2410.00938","title":"MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards","created":"2024-10-01","cited_by_count":7,"area":"moe"},{"id":"2410.22782","title":"MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning","created":"2024-10-30","cited_by_count":7,"area":null},{"id":"2501.07890","title":"GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism","created":"2025-01-14","cited_by_count":7,"area":"lr"},{"id":"2408.01505","title":"MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts","created":"2024-08-02","cited_by_count":6,"area":null},{"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":"2512.03125","title":"Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models","created":"2025-12-02","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":"2603.12658","title":"Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2408.10276","title":"FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models","created":"2024-08-17","cited_by_count":5,"area":null},{"id":"2505.20006","title":"Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.11638","title":"LoRA-Gen: Specializing Large Language Model via Online LoRA Generation","created":"2025-06-13","cited_by_count":5,"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":"2601.04823","title":"DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models","created":"2026-01-08","cited_by_count":5,"area":"moe"},{"id":"2605.05676","title":"Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2406.17484","title":"MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation","created":"2024-06-25","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":"2412.18729","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","created":"2024-12-25","cited_by_count":4,"area":null},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2502.03029","title":"On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation","created":"2025-02-05","cited_by_count":4,"area":null},{"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":"2511.01463","title":"HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA","created":"2025-11-03","cited_by_count":4,"area":"moe"},{"id":"2512.19765","title":"How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts","created":"2025-12-21","cited_by_count":4,"area":"moe"},{"id":"2603.12378","title":"NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation","created":"2026-03-12","cited_by_count":4,"area":"moe"},{"id":"2412.11483","title":"\"They've Stolen My GPL-Licensed Model!\": Toward Standardized and Transparent Model Licensing","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2504.06426","title":"S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning","created":"2025-04-08","cited_by_count":3,"area":"moe"},{"id":"2505.18640","title":"ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2505.23926","title":"Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation","created":"2025-05-29","cited_by_count":3,"area":"moe"},{"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":"2607.00162","title":"FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts","created":"2026-06-30","cited_by_count":3,"area":"moe"},{"id":"2407.11186","title":"Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"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,"area":null},{"id":"2502.03884","title":"Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning","created":"2025-02-06","cited_by_count":2,"area":"moe"},{"id":"2502.15455","title":"R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-Task Learning","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2503.09850","title":"TabNSA: Native Sparse Attention for Efficient Tabular Data Learning","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.23868","title":"Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE","created":"2025-05-29","cited_by_count":2,"area":"moe"},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2509.14900","title":"FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts","created":"2025-09-18","cited_by_count":2,"area":"moe"},{"id":"2512.05359","title":"Group Orthogonal Low-Rank Adaptation for RGB-T Tracking","created":"2025-12-05","cited_by_count":2,"area":null},{"id":"2512.06835","title":"Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning","created":"2025-12-07","cited_by_count":2,"area":"lr"},{"id":"2512.12880","title":"Improving Recursive Transformers with Mixture of LoRAs","created":"2025-12-14","cited_by_count":2,"area":null},{"id":"2601.06356","title":"Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning","created":"2026-01-09","cited_by_count":2,"area":"moe"},{"id":"2601.22647","title":"Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments","created":"2026-01-30","cited_by_count":2,"area":"wm"},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","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":"2603.26299","title":"Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy","created":"2026-03-27","cited_by_count":2,"area":null},{"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":"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":"2606.19549","title":"Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2607.04118","title":"Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.26052","title":"Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA","created":"2026-07-28","cited_by_count":2,"area":"moe"},{"id":"2608.02528","title":"Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2412.16216","title":"GMoE: Empowering LLMs Fine-Tuning via MoE Graph Collaboration","created":"2024-12-18","cited_by_count":1,"area":"moe"},{"id":"2502.15616","title":"Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2504.18147","title":"NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2506.01897","title":"MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.04487","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2508.05078","title":"From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2508.20295","title":"FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2601.10921","title":"RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2603.10160","title":"ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.17558","title":"Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition","created":"2026-03-18","cited_by_count":1,"area":null}],"next_cursor":"100"}