{"total":17,"rows":[{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"area":"moe"},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72,"area":"moe"},{"id":"2107.11817","title":"Go Wider Instead of Deeper","created":"2021-07-25","cited_by_count":57,"area":"moe"},{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38,"area":"moe"},{"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":"2407.19985","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","created":"2024-07-29","cited_by_count":25,"area":"moe"},{"id":"2402.02526","title":"CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition","created":"2024-02-04","cited_by_count":23,"area":"moe"},{"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":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2009.10622","title":"Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts","created":"2020-09-22","cited_by_count":6,"area":"moe"},{"id":"2312.16610","title":"Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation","created":"2023-12-27","cited_by_count":5,"area":"moe"},{"id":"2410.08003","title":"More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing","created":"2024-10-10","cited_by_count":2,"area":"moe"},{"id":"2410.09687","title":"MoIN: Mixture of Introvert Experts to Upcycle an LLM","created":"2024-10-13","cited_by_count":0,"area":"moe"},{"id":"2601.19811","title":"Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts","created":"2026-01-27","cited_by_count":0,"area":"moe"},{"id":"2602.07997","title":"Fast Model Selection and Stable Optimization for Softmax-Gated Multinomial-Logistic Mixture of Experts Models","created":"2026-02-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}