{"total":29,"rows":[{"id":"2410.10814","title":"Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free","created":"2024-10-14","cited_by_count":37,"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":"2206.00059","title":"A Mixture-of-Expert Approach to RL-based Dialogue Management","created":"2022-05-31","cited_by_count":16,"area":"moe"},{"id":"2512.23447","title":"Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss","created":"2025-12-29","cited_by_count":11,"area":"moe"},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2508.11999","title":"MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding","created":"2025-08-16","cited_by_count":7,"area":"moe"},{"id":"2309.00380","title":"Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives","created":"2023-09-01","cited_by_count":4,"area":"moe"},{"id":"2505.17553","title":"CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning","created":"2025-05-23","cited_by_count":4,"area":"moe"},{"id":"2605.24956","title":"NITP: Next Implicit Token Prediction for LLM Pre-training","created":"2026-05-24","cited_by_count":4,"area":"moe"},{"id":"2306.05011","title":"Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce","created":"2023-06-08","cited_by_count":3,"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":"2503.23007","title":"S2MoE: Robust Sparse Mixture of Experts via Stochastic Learning","created":"2025-03-29","cited_by_count":1,"area":"moe"},{"id":"2511.12922","title":"Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based Recommendation","created":"2025-11-17","cited_by_count":1,"area":"moe"},{"id":"2603.16649","title":"Mixture of Style Experts for Diverse Image Stylization","created":"2026-03-17","cited_by_count":1,"area":"moe"},{"id":"2603.22317","title":"Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning","created":"2026-03-20","cited_by_count":1,"area":"moe"},{"id":"2605.28459","title":"REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2509.14269","title":"SparseDoctor: Towards Efficient Chat Doctor with Mixture of Experts Enhanced Large Language Models","created":"2025-09-15","cited_by_count":0,"area":"moe"},{"id":"2511.11232","title":"DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts","created":"2025-11-14","cited_by_count":0,"area":"moe"},{"id":"2603.04320","title":"CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation","created":"2026-03-04","cited_by_count":0,"area":"moe"},{"id":"2604.12026","title":"TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness Prediction","created":"2026-04-13","cited_by_count":0,"area":"moe"},{"id":"2605.03348","title":"Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts","created":"2026-05-05","cited_by_count":0,"area":"moe"},{"id":"2605.08809","title":"SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization","created":"2026-05-09","cited_by_count":0,"area":"moe"},{"id":"2608.01060","title":"One Query, Many Scales: Sparse Mixture-of-Experts for Efficient Hierarchical Cross-View Geo-Localization","created":"2026-08-02","cited_by_count":0,"area":"moe"},{"id":"2608.04013","title":"C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning","created":"2026-04-22","cited_by_count":0,"area":"moe"},{"id":"2608.11699","title":"STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2608.23806","title":"Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings","created":"2026-08-24","cited_by_count":0,"area":"moe"},{"id":"2609.02204","title":"TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval","created":"2026-09-02","cited_by_count":0,"area":"moe"},{"id":"2609.39445","title":"Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.01921","title":"Cross-Lingual Alignment for Decoder-Only Models using MoE Routers","created":"2026-10-01","cited_by_count":0,"area":"moe"}],"next_cursor":null}