| Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective | Feb 1, 2025 | Mixture-of-Experts | —Unverified | 0 |
| Pheromone-based Learning of Optimal Reasoning Paths | Jan 31, 2025 | ARCGSM8K | —Unverified | 0 |
| Adaptive Prompt: Unlocking the Power of Visual Prompt Tuning | Jan 31, 2025 | Mixture-of-ExpertsVisual Prompt Tuning | —Unverified | 0 |
| MolGraph-xLSTM: A graph-based dual-level xLSTM framework with multi-head mixture-of-experts for enhanced molecular representation and interpretability | Jan 30, 2025 | Drug DiscoveryMixture-of-Experts | —Unverified | 0 |
| Heuristic-Informed Mixture of Experts for Link Prediction in Multilayer Networks | Jan 29, 2025 | Link PredictionMixture-of-Experts | —Unverified | 0 |
| Free Agent in Agent-Based Mixture-of-Experts Generative AI Framework | Jan 29, 2025 | Fraud DetectionMixture-of-Experts | —Unverified | 0 |
| 3D-MoE: A Mixture-of-Experts Multi-modal LLM for 3D Vision and Pose Diffusion via Rectified Flow | Jan 28, 2025 | Instruction FollowingMixture-of-Experts | —Unverified | 0 |
| Static Batching of Irregular Workloads on GPUs: Framework and Application to Efficient MoE Model Inference | Jan 27, 2025 | GPUMixture-of-Experts | —Unverified | 0 |
| ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning | Jan 25, 2025 | Mixture-of-Experts | —Unverified | 0 |
| Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning | Jan 25, 2025 | Mixture-of-ExpertsMulti-Task Learning | —Unverified | 0 |
