{"total":13,"rows":[{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2508.15763","title":"Intern-S1: A Scientific Multimodal Foundation Model","created":"2025-08-21","cited_by_count":53,"area":"moe"},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2502.05172","title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient","created":"2025-02-07","cited_by_count":31,"area":"moe"},{"id":"2410.05661","title":"Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models","created":"2024-10-08","cited_by_count":25,"area":"moe"},{"id":"2509.23678","title":"Towards a Comprehensive Scaling Law of Mixture-of-Experts","created":"2025-09-28","cited_by_count":10,"area":"moe"},{"id":"2509.24406","title":"Muon: Training and Trade-offs with Latent Attention and MoE","created":"2025-09-29","cited_by_count":3,"area":"moe"},{"id":"2512.13705","title":"Scaling and Transferability of Annealing Strategies in Large Language Model Training","created":"2025-12-05","cited_by_count":1,"area":"moe"},{"id":"2605.11255","title":"HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model","created":"2026-05-11","cited_by_count":1,"area":"moe"},{"id":"2609.01244","title":"Post-Training Science for Supervised Fine-Tuning","created":"2026-09-01","cited_by_count":1,"area":"moe"},{"id":"2609.08690","title":"Hyperparameter Scaling Laws Across MoE Sparsity","created":"2026-09-08","cited_by_count":0,"area":"moe"},{"id":"2609.36070","title":"Mixture-of-Kittens: MoE Megakernel for NVL72s","created":"2026-09-28","cited_by_count":0,"area":"moe"}],"next_cursor":null}