{"total":399,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396,"area":null},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"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":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"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":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232,"area":"mllm"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204,"area":null},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203,"area":"moe"},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203,"area":null},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187,"area":"moe"},{"id":"2303.16854","title":"AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators","created":"2023-03-29","cited_by_count":172,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"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":"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":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138,"area":"moe"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"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":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102,"area":"moe"},{"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":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92,"area":"moe"},{"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":"2505.22159","title":"ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation","created":"2025-05-28","cited_by_count":91,"area":"vla"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76,"area":"mllm"},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72,"area":"moe"},{"id":"2403.07652","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","created":"2024-03-12","cited_by_count":72,"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":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2509.01322","title":"LongCat-Flash Technical Report","created":"2025-09-01","cited_by_count":58,"area":"agents"},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2509.24389","title":"LLaDA-MoE: A Sparse MoE Diffusion Language Model","created":"2025-09-29","cited_by_count":57,"area":"diffusion"},{"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":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54,"area":"moe"},{"id":"2501.11873","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","created":"2025-01-21","cited_by_count":54,"area":"moe"},{"id":"2304.03946","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","created":"2023-04-08","cited_by_count":53,"area":"moe"},{"id":"2501.12370","title":"Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models","created":"2025-01-21","cited_by_count":50,"area":"moe"},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"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":"2406.18219","title":"A Closer Look into Mixture-of-Experts in Large Language Models","created":"2024-06-26","cited_by_count":48,"area":"moe"},{"id":"2309.00810","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","created":"2023-09-02","cited_by_count":47,"area":"diffusion"},{"id":"2409.03277","title":"ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding","created":"2024-09-05","cited_by_count":46,"area":"moe"},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"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":"2404.05089","title":"SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts","created":"2024-04-07","cited_by_count":40,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"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":"2407.09590","title":"Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts","created":"2024-07-12","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":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"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":"2404.05019","title":"Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts","created":"2024-04-07","cited_by_count":32,"area":"moe"},{"id":"2502.07972","title":"Training Sparse Mixture Of Experts Text Embedding Models","created":"2025-02-11","cited_by_count":32,"area":"moe"},{"id":"2403.09176","title":"Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts","created":"2024-03-14","cited_by_count":31,"area":"diffusion"},{"id":"2502.05172","title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient","created":"2025-02-07","cited_by_count":31,"area":"moe"},{"id":"2407.15811","title":"Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget","created":"2024-07-22","cited_by_count":30,"area":"diffusion"},{"id":"2410.02098","title":"EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing","created":"2024-10-02","cited_by_count":30,"area":"diffusion"},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29,"area":null},{"id":"2507.13575","title":"Apple Intelligence Foundation Language Models: Tech Report 2025","created":"2025-07-17","cited_by_count":28,"area":"moe"},{"id":"2211.10017","title":"Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production","created":"2022-11-18","cited_by_count":27,"area":"moe"},{"id":"2507.13812","title":"SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing","created":"2025-07-18","cited_by_count":26,"area":null},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25,"area":null},{"id":"2308.11971","title":"EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE","created":"2023-08-23","cited_by_count":25,"area":"mllm"},{"id":"2212.01853","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","created":"2022-12-04","cited_by_count":24,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"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":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2506.14038","title":"Load Balancing Mixture of Experts with Similarity Preserving Routers","created":"2025-06-16","cited_by_count":22,"area":"moe"},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2407.20254","title":"EEGMamba: Bidirectional State Space Model with Mixture of Experts for EEG Multi-task Classification","created":"2024-07-20","cited_by_count":21,"area":"ssm"},{"id":"2408.06793","title":"Layerwise Recurrent Router for Mixture-of-Experts","created":"2024-08-13","cited_by_count":21,"area":"moe"},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2402.13089","title":"Towards an empirical understanding of MoE design choices","created":"2024-02-20","cited_by_count":20,"area":"moe"},{"id":"2410.10054","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","created":"2024-10-14","cited_by_count":20,"area":"moe"},{"id":"2504.05586","title":"Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations","created":"2025-04-08","cited_by_count":20,"area":"moe"},{"id":"2405.14507","title":"Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast","created":"2024-05-23","cited_by_count":19,"area":"moe"},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2312.10868","title":"From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape","created":"2023-12-18","cited_by_count":18,"area":"moe"},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2409.12136","title":"GRIN: GRadient-INformed MoE","created":"2024-09-18","cited_by_count":17,"area":"moe"},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2310.04361","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","created":"2023-10-06","cited_by_count":16,"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":"2408.11396","title":"MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing","created":"2024-08-21","cited_by_count":16,"area":"moe"},{"id":"2410.10456","title":"Ada-K Routing: Boosting the Efficiency of MoE-based LLMs","created":"2024-10-14","cited_by_count":16,"area":"moe"},{"id":"2412.05552","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","created":"2024-12-07","cited_by_count":16,"area":"moe"},{"id":"2411.01595","title":"RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering","created":"2024-11-03","cited_by_count":15,"area":"mllm"},{"id":"2503.05066","title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","created":"2025-03-07","cited_by_count":15,"area":"moe"},{"id":"2507.11181","title":"Mixture of Experts in Large Language Models","created":"2025-07-15","cited_by_count":15,"area":"moe"},{"id":"2405.09592","title":"A Survey of Generative Techniques for Spatial-Temporal Data Mining","created":"2024-05-15","cited_by_count":14,"area":null}],"next_cursor":"100"}