{"total":14,"rows":[{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"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":"2609.01343","title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","created":"2026-09-01","cited_by_count":18,"area":"moe"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2604.02178","title":"The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level","created":"2026-04-02","cited_by_count":7,"area":"moe"},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2606.04300","title":"Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval","created":"2026-06-03","cited_by_count":3,"area":"moe"},{"id":"2604.14434","title":"Geometric Routing Enables Causal Expert Control in Mixture of Experts","created":"2026-04-15","cited_by_count":2,"area":"moe"},{"id":"2604.17837","title":"Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs","created":"2026-04-20","cited_by_count":2,"area":"moe"},{"id":"2605.17598","title":"Mixture of Experts for Low-Resource LLMs","created":"2026-05-17","cited_by_count":1,"area":"moe"},{"id":"2509.14255","title":"Cosine-Similarity Routing with Semantic Anchors for Interpretable Mixture-of-Experts Language Models","created":"2025-09-12","cited_by_count":0,"area":"moe"},{"id":"2608.13565","title":"Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking","created":"2026-06-25","cited_by_count":0,"area":"moe"},{"id":"2608.15102","title":"A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models","created":"2026-08-15","cited_by_count":0,"area":"moe"},{"id":"2608.26650","title":"Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs","created":"2026-08-27","cited_by_count":0,"area":"moe"}],"next_cursor":null}