| AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale | May 13, 2025 | Mixture-of-Experts | —Unverified | 0 |
| UMoE: Unifying Attention and FFN with Shared Experts | May 12, 2025 | Mixture-of-Experts | —Unverified | 0 |
| Seed1.5-VL Technical Report | May 11, 2025 | Mixture-of-ExpertsMultimodal Reasoning | —Unverified | 0 |
| FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers | May 11, 2025 | Computational EfficiencyMixture-of-Experts | —Unverified | 0 |
| The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts | May 11, 2025 | Mixture-of-Experts | —Unverified | 0 |
| QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration | May 10, 2025 | GPUMixture-of-Experts | —Unverified | 0 |
| FloE: On-the-Fly MoE Inference on Memory-constrained GPU | May 9, 2025 | CPUGPU | —Unverified | 0 |
| Divide-and-Conquer: Cold-Start Bundle Recommendation via Mixture of Diffusion Experts | May 8, 2025 | Mixture-of-Experts | —Unverified | 0 |
| SToLa: Self-Adaptive Touch-Language Framework with Tactile Commonsense Reasoning in Open-Ended Scenarios | May 7, 2025 | DiversityMixture-of-Experts | —Unverified | 0 |
| LLM-e Guess: Can LLMs Capabilities Advance Without Hardware Progress? | May 7, 2025 | Large Language ModelMixture-of-Experts | CodeCode Available | 0 |
