| MLP-KAN: Unifying Deep Representation and Function Learning | Oct 3, 2024 | Kolmogorov-Arnold NetworksMixture-of-Experts | CodeCode Available | 0 |
| Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts | Oct 3, 2024 | Mixture-of-Expertsparameter estimation | CodeCode Available | 0 |
| Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping | Oct 3, 2024 | GPUMixture-of-Experts | —Unverified | 0 |
| Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices | Oct 3, 2024 | Mixture-of-Experts | CodeCode Available | 1 |
| Neutral residues: revisiting adapters for model extension | Oct 3, 2024 | Domain AdaptationLanguage Modelling | —Unverified | 0 |
| EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing | Oct 2, 2024 | Image GenerationMixture-of-Experts | —Unverified | 0 |
| Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging | Oct 2, 2024 | DiversityMixture-of-Experts | —Unverified | 0 |
| The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs | Oct 2, 2024 | BenchmarkingHallucination | —Unverified | 0 |
| Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models | Oct 2, 2024 | Mixture-of-ExpertsNavigate | CodeCode Available | 2 |
| UniAdapt: A Universal Adapter for Knowledge Calibration | Oct 1, 2024 | Mixture-of-ExpertsModel Editing | —Unverified | 0 |
