{"total":56,"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":"2410.13025","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","created":"2024-10-16","cited_by_count":52,"area":null},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"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":"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":"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":"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":"2512.23447","title":"Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss","created":"2025-12-29","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":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2411.04712","title":"SEE-DPO: Self Entropy Enhanced Direct Preference Optimization","created":"2024-11-06","cited_by_count":7,"area":"diffusion"},{"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":"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":"2505.24449","title":"When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations","created":"2025-05-30","cited_by_count":7,"area":"mllm"},{"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":"2505.21226","title":"Why Do More Experts Fail? A Theoretical Analysis of Model Merging","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2510.23123","title":"Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation","created":"2025-10-27","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":"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":"2506.14436","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":"2510.19733","title":"Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning","created":"2025-10-22","cited_by_count":5,"area":null},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2508.06953","title":"BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2511.01463","title":"HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA","created":"2025-11-03","cited_by_count":4,"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":"2604.05336","title":"TRACE: Capability-Targeted Agentic Training","created":"2026-04-07","cited_by_count":3,"area":"agents"},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2412.20064","title":"VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2503.09662","title":"CoRe^2: Collect, Reflect and Refine to Generate Better and Faster","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2503.21227","title":"LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models","created":"2025-03-27","cited_by_count":2,"area":"mllm"},{"id":"2503.23362","title":"Mixture of Routers","created":"2025-03-30","cited_by_count":2,"area":"alignment"},{"id":"2506.11999","title":"Generative Representational Learning of Foundation Models for Recommendation","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2508.06831","title":"Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification","created":"2025-08-09","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":"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":"2604.01310","title":"Sparse Spectral LoRA: Routed Experts for Medical VLMs","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2604.04857","title":"The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models","created":"2026-04-06","cited_by_count":1,"area":"mllm"},{"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":"2605.25565","title":"RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism","created":"2026-05-25","cited_by_count":1,"area":"moe"},{"id":"2511.03005","title":"Error-Aware Knowledge Distillation via Targeted Revision for Customer-Service Summarization","created":"2025-11-04","cited_by_count":0,"area":"distill"},{"id":"2602.08755","title":"Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations","created":"2026-02-09","cited_by_count":0,"area":"moe"},{"id":"2603.12577","title":"Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation","created":"2026-03-13","cited_by_count":0,"area":"moe"},{"id":"2605.08423","title":"Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.29375","title":"TriageRA-CCF: Source-Side Clinical Confidence and Coverage Signals for Adaptive Rank Budgeting in Medical LLMs","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2606.31432","title":"Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2610.06765","title":"Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08049","title":"A Riemannian Geometry for Low-rank Adaptation","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.12256","title":"Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}