{"total":57,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"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":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2410.07348","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","created":"2024-10-09","cited_by_count":56,"area":"moe"},{"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":"2405.03133","title":"Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training","created":"2024-05-06","cited_by_count":37,"area":"moe"},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2408.13359","title":"Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler","created":"2024-08-23","cited_by_count":28,"area":null},{"id":"2407.01906","title":"Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models","created":"2024-07-02","cited_by_count":21,"area":"moe"},{"id":"2408.08274","title":"BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts","created":"2024-08-15","cited_by_count":16,"area":"moe"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2410.02117","title":"Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices","created":"2024-10-03","cited_by_count":13,"area":"moe"},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"id":"2508.01483","title":"Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2605.18106","title":"Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers","created":"2026-05-18","cited_by_count":11,"area":"moe"},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2510.14436","title":"MergeMoE: Efficient Compression of MoE Models via Expert Output Merging","created":"2025-10-16","cited_by_count":10,"area":"moe"},{"id":"2406.12375","title":"GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory","created":"2024-06-18","cited_by_count":8,"area":"moe"},{"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":"2603.04971","title":"Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation","created":"2026-03-05","cited_by_count":8,"area":"moe"},{"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":"2501.16295","title":"Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity","created":"2025-01-27","cited_by_count":7,"area":"ssm"},{"id":"2504.07964","title":"C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing","created":"2025-04-10","cited_by_count":7,"area":"moe"},{"id":"2501.09410","title":"MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models","created":"2025-01-16","cited_by_count":6,"area":"moe"},{"id":"2503.05447","title":"Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts","created":"2025-03-07","cited_by_count":6,"area":"moe"},{"id":"2509.25913","title":"Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel","created":"2025-09-30","cited_by_count":6,"area":"moe"},{"id":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"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":"2503.05029","title":"Continual Pre-training of MoEs: How robust is your router?","created":"2025-03-06","cited_by_count":5,"area":"moe"},{"id":"2505.20225","title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","created":"2025-05-26","cited_by_count":5,"area":"moe"},{"id":"2408.04278","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2503.21135","title":"DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation","created":"2025-03-27","cited_by_count":4,"area":"moe"},{"id":"2505.13345","title":"Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference","created":"2025-05-19","cited_by_count":4,"area":"moe"},{"id":"2506.18233","title":"Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2508.09591","title":"HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap","created":"2025-08-13","cited_by_count":4,"area":"moe"},{"id":"2405.09274","title":"Dynamic Activation Pitfalls in LLaMA Models: An Empirical Study","created":"2024-05-15","cited_by_count":3,"area":null},{"id":"2605.08292","title":"Hierarchical Mixture-of-Experts with Two-Stage Optimization","created":"2026-05-08","cited_by_count":3,"area":"moe"},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.14053","title":"Position: Require Frontier AI Labs To Release Small \"Analog\" Models","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"area":"moe"},{"id":"2404.19484","title":"More Compute Is What You Need","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2502.17187","title":"Evaluating Expert Contributions in a MoE LLM for Quiz-Based Tasks","created":"2025-02-24","cited_by_count":0,"area":"moe"},{"id":"2509.20073","title":"SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Heads","created":"2025-09-24","cited_by_count":0,"area":"moe"},{"id":"2512.13727","title":"RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing","created":"2025-12-13","cited_by_count":0,"area":"moe"},{"id":"2603.27624","title":"Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling","created":"2026-03-29","cited_by_count":0,"area":"moe"},{"id":"2605.06501","title":"Cubit: Token Mixer with Kernel Ridge Regression","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.11537","title":"Fast MoE Inference via Predictive Prefetching and Expert Replication","created":"2026-05-12","cited_by_count":0,"area":"moe"},{"id":"2608.08650","title":"The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert Parallelism","created":"2026-08-09","cited_by_count":0,"area":"moe"},{"id":"2609.17940","title":"Beyond the Previous Layer: Residual Predictive Structure in Sparse MoE Routing","created":"2026-09-15","cited_by_count":0,"area":"moe"},{"id":"2610.04140","title":"ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training","created":"2026-10-02","cited_by_count":0,"area":"moe"}],"next_cursor":null}