{"total":15,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15,"area":"moe"},{"id":"2504.07964","title":"C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing","created":"2025-04-10","cited_by_count":7,"area":"moe"},{"id":"2511.07419","title":"Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs","created":"2025-11-10","cited_by_count":7,"area":"moe"},{"id":"2601.08383","title":"Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models","created":"2026-01-13","cited_by_count":4,"area":"moe"},{"id":"2512.13996","title":"DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training","created":"2025-12-16","cited_by_count":3,"area":"moe"},{"id":"2606.05378","title":"Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models","created":"2026-06-03","cited_by_count":2,"area":"moe"},{"id":"2606.02378","title":"When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures","created":"2026-06-01","cited_by_count":1,"area":"moe"},{"id":"2608.25231","title":"Output Dilution: Redundant but Fragile Representations in MoE Models","created":"2026-08-25","cited_by_count":1,"area":"moe"},{"id":"2506.16600","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","created":"2025-06-19","cited_by_count":0,"area":"moe"},{"id":"2604.00785","title":"Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer","created":"2026-04-01","cited_by_count":0,"area":"moe"},{"id":"2605.16690","title":"UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models","created":"2026-05-15","cited_by_count":0,"area":"moe"},{"id":"2609.00791","title":"Instella-MoE Technical Report","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2609.13486","title":"Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2610.05458","title":"Measuring and Reducing Cross-Vendor Mismatch in Language Models","created":"2026-10-04","cited_by_count":0,"area":"moe"}],"next_cursor":null}