{"total":15,"rows":[{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2402.07033","title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models","created":"2024-02-10","cited_by_count":71,"area":"moe"},{"id":"2410.08589","title":"Retraining-Free Merging of Sparse MoE via Hierarchical Clustering","created":"2024-10-11","cited_by_count":35,"area":"moe"},{"id":"2405.13053","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","created":"2024-05-19","cited_by_count":16,"area":"moe"},{"id":"2409.15161","title":"A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Experts","created":"2024-09-23","cited_by_count":6,"area":"moe"},{"id":"2605.20948","title":"Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory","created":"2026-05-20","cited_by_count":5,"area":"moe"},{"id":"2506.18145","title":"Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection","created":"2025-06-22","cited_by_count":4,"area":"moe"},{"id":"2405.06059","title":"A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds","created":"2024-05-09","cited_by_count":2,"area":"moe"},{"id":"2601.05296","title":"MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs","created":"2026-01-08","cited_by_count":2,"area":"moe"},{"id":"2601.07022","title":"Solar Open Technical Report","created":"2026-01-11","cited_by_count":2,"area":"moe"},{"id":"2603.13719","title":"Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking","created":"2026-03-14","cited_by_count":0,"area":"moe"},{"id":"2605.08575","title":"Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution","created":"2026-05-09","cited_by_count":0,"area":"moe"},{"id":"2605.09403","title":"Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers","created":"2026-05-10","cited_by_count":0,"area":"moe"},{"id":"2605.31302","title":"MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstruction","created":"2026-05-29","cited_by_count":0,"area":"moe"},{"id":"2608.14385","title":"DeaMoE: Efficient MoE Structure for Fast Small-Batch Decoding","created":"2026-08-14","cited_by_count":0,"area":"moe"}],"next_cursor":null}