| GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks | Oct 12, 2024 | Mixture-of-Experts | —Unverified | 0 |
| Retraining-Free Merging of Sparse MoE via Hierarchical Clustering | Oct 11, 2024 | ClusteringLanguage Modeling | CodeCode Available | 1 |
| Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts | Oct 10, 2024 | Mixture-of-Experts | CodeCode Available | 2 |
| More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing | Oct 10, 2024 | image-classificationImage Classification | CodeCode Available | 0 |
| Upcycling Large Language Models into Mixture of Experts | Oct 10, 2024 | Mixture-of-ExpertsMMLU | —Unverified | 0 |
| Efficient Dictionary Learning with Switch Sparse Autoencoders | Oct 10, 2024 | Dictionary LearningMixture-of-Experts | CodeCode Available | 1 |
| Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training | Oct 10, 2024 | Mixture-of-ExpertsVisual Question Answering | —Unverified | 0 |
| MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts | Oct 9, 2024 | GPUMixture-of-Experts | CodeCode Available | 4 |
| Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs | Oct 9, 2024 | Common Sense ReasoningMixture-of-Experts | —Unverified | 0 |
| Toward generalizable learning of all (linear) first-order methods via memory augmented Transformers | Oct 8, 2024 | AllMixture-of-Experts | —Unverified | 0 |
