{"total":96,"rows":[{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"area":"moe"},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"area":"inference"},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300,"area":"mllm"},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150,"area":"moe"},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148,"area":"moe"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66,"area":"moe"},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65,"area":"moe"},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2204.07689","title":"Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners","created":"2022-04-16","cited_by_count":51,"area":"moe"},{"id":"2405.01413","title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","created":"2024-05-02","cited_by_count":49,"area":"mllm"},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38,"area":null},{"id":"2303.06182","title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference","created":"2023-03-10","cited_by_count":37,"area":"moe"},{"id":"2310.09832","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","created":"2023-10-15","cited_by_count":37,"area":"moe"},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"area":null},{"id":"2310.02410","title":"Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness","created":"2023-10-03","cited_by_count":34,"area":"moe"},{"id":"2311.09179","title":"SiRA: Sparse Mixture of Low Rank Adaptation","created":"2023-11-15","cited_by_count":32,"area":"moe"},{"id":"2203.01104","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","created":"2022-03-02","cited_by_count":31,"area":"moe"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2403.13358","title":"GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot","created":"2024-03-20","cited_by_count":29,"area":"moe"},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28,"area":null},{"id":"2308.15030","title":"SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget","created":"2023-08-29","cited_by_count":27,"area":"moe"},{"id":"2404.08452","title":"MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection","created":"2024-04-12","cited_by_count":27,"area":"moe"},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2312.05662","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","created":"2023-12-09","cited_by_count":19,"area":null},{"id":"2401.13920","title":"LocMoE: A Low-Overhead MoE for Large Language Model Training","created":"2024-01-25","cited_by_count":19,"area":"moe"},{"id":"2302.14703","title":"Improving Expert Specialization in Mixture of Experts","created":"2023-02-28","cited_by_count":17,"area":"moe"},{"id":"2402.05382","title":"Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts","created":"2024-02-08","cited_by_count":16,"area":"moe"},{"id":"2407.14093","title":"Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2305.02665","title":"Learning Language-Specific Layers for Multilingual Machine Translation","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2303.13739","title":"WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal","created":"2023-03-24","cited_by_count":11,"area":"moe"},{"id":"2406.19905","title":"Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model","created":"2024-06-28","cited_by_count":11,"area":"mllm"},{"id":"2503.06823","title":"eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference","created":"2025-03-10","cited_by_count":11,"area":"moe"},{"id":"2203.03312","title":"SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding","created":"2022-03-07","cited_by_count":10,"area":null},{"id":"2210.07535","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","created":"2022-10-14","cited_by_count":10,"area":"moe"},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","cited_by_count":10,"area":null},{"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":"2410.23274","title":"Multi-student Diffusion Distillation for Better One-step Generators","created":"2024-10-30","cited_by_count":10,"area":"diffusion"},{"id":"2312.03248","title":"Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning","created":"2023-12-06","cited_by_count":8,"area":null},{"id":"2409.01483","title":"Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning","created":"2024-09-02","cited_by_count":8,"area":"moe"},{"id":"2207.10341","title":"UFO: Unified Feature Optimization","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2312.08881","title":"Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts","created":"2023-12-12","cited_by_count":7,"area":"moe"},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2406.07007","title":"Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2212.09666","title":"MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code Completion","created":"2022-12-19","cited_by_count":6,"area":"moe"},{"id":"2305.18952","title":"Exploring the Practicality of Generative Retrieval on Dynamic Corpora","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2407.00875","title":"MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting","created":"2024-06-25","cited_by_count":6,"area":"moe"},{"id":"2404.16407","title":"U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF","created":"2024-04-25","cited_by_count":5,"area":"moe"},{"id":"2503.02354","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2507.14456","title":"GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving","created":"2025-07-19","cited_by_count":5,"area":"driving"},{"id":"2308.04215","title":"Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction","created":"2023-08-08","cited_by_count":4,"area":"rag"},{"id":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2402.01911","title":"From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2508.19667","title":"Survey of Specialized Large Language Model","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2512.02351","title":"Understanding and Harnessing Sparsity in Unified Multimodal Models","created":"2025-12-02","cited_by_count":4,"area":"mllm"},{"id":"2603.00054","title":"Expert Divergence Learning for MoE-based Language Models","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2211.17142","title":"Learning Label Modular Prompts for Text Classification in the Wild","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2305.02176","title":"Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity","created":"2023-05-03","cited_by_count":3,"area":"moe"},{"id":"2305.13993","title":"Condensing Multilingual Knowledge with Lightweight Language-Specific Modules","created":"2023-05-23","cited_by_count":3,"area":"moe"},{"id":"2307.04052","title":"Learning to Group Auxiliary Datasets for Molecule","created":"2023-07-08","cited_by_count":3,"area":null},{"id":"2410.23507","title":"Efficient and Interpretable Grammatical Error Correction with Mixture of Experts","created":"2024-10-30","cited_by_count":3,"area":"moe"},{"id":"2509.10513","title":"Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning","created":"2025-09-03","cited_by_count":3,"area":"moe"},{"id":"2306.02824","title":"COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search","created":"2023-06-05","cited_by_count":2,"area":"moe"},{"id":"2306.11027","title":"JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving","created":"2023-06-19","cited_by_count":2,"area":"lr"},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2504.05318","title":"Efficient Multi-Task Learning via Generalist Recommender","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.08744","title":"ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses","created":"2025-03-23","cited_by_count":2,"area":"rag"},{"id":"2505.14173","title":"THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation","created":"2025-05-20","cited_by_count":2,"area":"moe"},{"id":"2506.11999","title":"Generative Representational Learning of Foundation Models for Recommendation","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2604.23996","title":"SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs","created":"2026-04-27","cited_by_count":2,"area":"mllm"},{"id":"2210.11628","title":"Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2407.01126","title":"Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation","created":"2024-07-01","cited_by_count":1,"area":"moe"},{"id":"2603.29765","title":"Training-Free Dynamic Upcycling of Expert Language Models","created":"2026-03-31","cited_by_count":1,"area":"moe"},{"id":"2310.12236","title":"Direct Neural Machine Translation with Task-level Mixture of Experts models","created":"2023-10-18","cited_by_count":0,"area":"moe"},{"id":"2402.17934","title":"Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2503.06003","title":"Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models","created":"2025-03-08","cited_by_count":0,"area":"mllm"},{"id":"2509.19781","title":"Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference","created":"2025-09-24","cited_by_count":0,"area":"moe"},{"id":"2604.03342","title":"Mixture-of-Experts in Remote Sensing: A Survey","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2606.14398","title":"A theoretical model for task routing in mixture-of-expert transformers","created":"2026-06-12","cited_by_count":0,"area":"moe"},{"id":"2608.02129","title":"PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.24372","title":"Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}