{"total":22,"rows":[{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"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":"2406.11256","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","created":"2024-06-17","cited_by_count":19,"area":"moe"},{"id":"2506.10357","title":"Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization","created":"2025-06-12","cited_by_count":13,"area":"moe"},{"id":"2506.21551","title":"Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test","created":"2025-06-26","cited_by_count":10,"area":"moe"},{"id":"2510.00844","title":"Learning Compact Representations of LLM Abilities via Item Response Theory","created":"2025-10-01","cited_by_count":10,"area":"moe"},{"id":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2505.14136","title":"Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging","created":"2025-05-20","cited_by_count":9,"area":"moe"},{"id":"2412.11864","title":"Investigating Mixture of Experts in Dense Retrieval","created":"2024-12-16","cited_by_count":4,"area":"moe"},{"id":"2508.04645","title":"A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation","created":"2025-08-06","cited_by_count":2,"area":"moe"},{"id":"2510.15683","title":"Mixture of Experts Approaches in Dense Retrieval Tasks","created":"2025-10-17","cited_by_count":2,"area":"moe"},{"id":"2401.15713","title":"Contrastive Learning and Mixture of Experts Enables Precise Vector Embeddings","created":"2024-01-28","cited_by_count":1,"area":"moe"},{"id":"2602.00067","title":"Modality as Heterogeneity: Node Splitting and Graph Rewiring for Multimodal Graph Learning","created":"2026-01-20","cited_by_count":1,"area":"moe"},{"id":"2605.28577","title":"Continual Model Routing in Evolving Model Hubs","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2406.02969","title":"Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models","created":"2024-06-05","cited_by_count":0,"area":"moe"},{"id":"2512.21897","title":"MMCTOP: A Multimodal Textualization and Mixture-of-Experts Framework for Clinical Trial Outcome Prediction","created":"2025-12-26","cited_by_count":0,"area":"moe"},{"id":"2602.14039","title":"Geometry-Preserving Aggregation for Mixture-of-Experts Embedding Models","created":"2026-02-15","cited_by_count":0,"area":"moe"},{"id":"2602.18929","title":"Give Users the Wheel: Towards Promptable Recommendation Paradigm","created":"2026-02-21","cited_by_count":0,"area":"moe"},{"id":"2605.22779","title":"FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection","created":"2026-05-21","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":"2610.11775","title":"RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing","created":"2026-10-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}