{"total":148,"rows":[{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823,"area":"moe"},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657,"area":null},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"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":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123,"area":"moe"},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2210.15257","title":"ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts","created":"2022-10-27","cited_by_count":112,"area":"diffusion"},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2402.00433","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","created":"2024-02-01","cited_by_count":85,"area":"moe"},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2405.01029","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","created":"2024-05-02","cited_by_count":70,"area":"moe"},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2405.05949","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","created":"2024-05-09","cited_by_count":56,"area":"mllm"},{"id":"2406.15007","title":"RouteFinder: Towards Foundation Models for Vehicle Routing Problems","created":"2024-06-21","cited_by_count":55,"area":null},{"id":"2410.07524","title":"Upcycling Large Language Models into Mixture of Experts","created":"2024-10-10","cited_by_count":49,"area":"moe"},{"id":"2406.11909","title":"Mixture-of-Subspaces in Low-Rank Adaptation","created":"2024-06-16","cited_by_count":47,"area":"diffusion"},{"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":"2412.13736","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","created":"2024-12-18","cited_by_count":46,"area":"lr"},{"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":"2502.16534","title":"Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs","created":"2025-02-23","cited_by_count":39,"area":null},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2403.03432","title":"Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models","created":"2024-03-06","cited_by_count":38,"area":"moe"},{"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":"2402.01771","title":"BlackMamba: Mixture of Experts for State-Space Models","created":"2024-02-01","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":"2405.00361","title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","created":"2024-05-01","cited_by_count":34,"area":null},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2309.13850","title":"Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts","created":"2023-09-25","cited_by_count":29,"area":"moe"},{"id":"2402.15505","title":"Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts","created":"2024-02-23","cited_by_count":28,"area":"moe"},{"id":"2408.11304","title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","created":"2024-08-21","cited_by_count":27,"area":"moe"},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2401.15969","title":"Routers in Vision Mixture of Experts: An Empirical Study","created":"2024-01-29","cited_by_count":23,"area":"moe"},{"id":"2402.02952","title":"On Least Square Estimation in Softmax Gating Mixture of Experts","created":"2024-02-05","cited_by_count":23,"area":"moe"},{"id":"2409.19291","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","created":"2024-09-28","cited_by_count":23,"area":"moe"},{"id":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23,"area":"moe"},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2410.15774","title":"Generalizing Motion Planners with Mixture of Experts for Autonomous Driving","created":"2024-10-21","cited_by_count":22,"area":"driving"},{"id":"2312.07035","title":"HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts","created":"2023-12-12","cited_by_count":21,"area":"moe"},{"id":"2306.02003","title":"On Optimal Caching and Model Multiplexing for Large Model Inference","created":"2023-06-03","cited_by_count":20,"area":null},{"id":"2312.04693","title":"GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts","created":"2023-12-07","cited_by_count":19,"area":"moe"},{"id":"2406.11256","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","created":"2024-06-17","cited_by_count":19,"area":"moe"},{"id":"2501.04004","title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes","created":"2025-01-07","cited_by_count":19,"area":"moe"},{"id":"2506.17368","title":"SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification","created":"2025-06-20","cited_by_count":18,"area":"alignment"},{"id":"2305.07572","title":"Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts","created":"2023-05-12","cited_by_count":17,"area":"moe"},{"id":"2408.12733","title":"SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging","created":"2024-08-22","cited_by_count":16,"area":"moe"},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","cited_by_count":15,"area":null},{"id":"2409.06669","title":"DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models","created":"2024-09-10","cited_by_count":15,"area":"moe"},{"id":"2309.04354","title":"Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts","created":"2023-09-08","cited_by_count":14,"area":"moe"},{"id":"2412.00099","title":"Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference","created":"2024-11-27","cited_by_count":14,"area":"moe"},{"id":"2501.10375","title":"DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference","created":"2024-12-16","cited_by_count":14,"area":"moe"},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"area":null},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"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":"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":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","cited_by_count":10,"area":"moe"},{"id":"2305.13999","title":"Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model","created":"2023-05-23","cited_by_count":9,"area":"moe"},{"id":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2406.05845","title":"MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering","created":"2024-06-09","cited_by_count":9,"area":null},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2211.08253","title":"HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization","created":"2022-11-15","cited_by_count":8,"area":"moe"},{"id":"2408.12793","title":"La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection","created":"2024-08-23","cited_by_count":8,"area":"moe"},{"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":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2311.05185","title":"Mixture of Weak & Strong Experts on Graphs","created":"2023-11-09","cited_by_count":7,"area":null},{"id":"2406.11353","title":"$\\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts","created":"2024-06-17","cited_by_count":7,"area":"moe"},{"id":"2406.12923","title":"Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction","created":"2024-06-14","cited_by_count":7,"area":"moe"},{"id":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2412.16971","title":"Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models","created":"2024-12-22","cited_by_count":7,"area":"moe"},{"id":"2412.20875","title":"Attention Is All You Need For Mixture-of-Depths Routing","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2510.05781","title":"Mixture of Neuron Experts","created":"2025-10-07","cited_by_count":7,"area":"moe"},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2401.00816","title":"Glimpse: Generalized Locality for Scalable and Robust CT","created":"2024-01-01","cited_by_count":6,"area":null},{"id":"2404.09339","title":"Towards Practical Tool Usage for Continually Learning LLMs","created":"2024-04-14","cited_by_count":6,"area":"agents"},{"id":"2404.16356","title":"Integration of Mixture of Experts and Multimodal Generative AI in Internet of Vehicles: A Survey","created":"2024-04-25","cited_by_count":6,"area":"moe"},{"id":"2511.22103","title":"MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding","created":"2025-11-27","cited_by_count":6,"area":"moe"},{"id":"2308.15772","title":"Task-Based MoE for Multitask Multilingual Machine Translation","created":"2023-08-30","cited_by_count":5,"area":"moe"},{"id":"2502.01677","title":"Position: AI Scaling: From Up to Down and Out","created":"2025-02-02","cited_by_count":5,"area":null},{"id":"2502.14759","title":"On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems","created":"2025-02-20","cited_by_count":5,"area":"rag"},{"id":"2407.01409","title":"Dynamic Few-Shot Learning for Knowledge Graph Question Answering","created":"2024-07-01","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":"2502.11096","title":"Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference Time","created":"2025-02-16","cited_by_count":4,"area":"lr"},{"id":"2512.11843","title":"Spiking Manifesto","created":"2025-12-03","cited_by_count":4,"area":null},{"id":"2308.14969","title":"Uncovering the Hidden Cost of Model Compression","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2310.01154","title":"Modularity in Deep Learning: A Survey","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2402.02636","title":"Can Large Language Models Learn Independent Causal Mechanisms?","created":"2024-02-04","cited_by_count":3,"area":"lr"},{"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":"2501.17356","title":"On the Coexistence and Ensembling of Watermarks","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","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":"2505.17138","title":"RAP: Runtime Adaptive Pruning for LLM Inference","created":"2025-05-22","cited_by_count":3,"area":"inference"}],"next_cursor":"100"}