| Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection | Nov 26, 2024 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| H^3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs | Nov 26, 2024 | Mixture-of-Experts | CodeCode Available | 0 |
| MH-MoE: Multi-Head Mixture-of-Experts | Nov 25, 2024 | Mixture-of-Experts | —Unverified | 0 |
| LDACP: Long-Delayed Ad Conversions Prediction Model for Bidding Strategy | Nov 25, 2024 | Mixture-of-Expertsregression | —Unverified | 0 |
| LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training | Nov 24, 2024 | MathMixture-of-Experts | CodeCode Available | 2 |
| Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts | Nov 23, 2024 | knowledge editingMixture-of-Experts | —Unverified | 0 |
| MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification | Nov 20, 2024 | DecoderLanguage Modeling | —Unverified | 0 |
| KAAE: Numerical Reasoning for Knowledge Graphs via Knowledge-aware Attributes Learning | Nov 20, 2024 | AttributeContrastive Learning | —Unverified | 0 |
| Ultra-Sparse Memory Network | Nov 19, 2024 | Mixture-of-Experts | —Unverified | 0 |
| CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters | Nov 18, 2024 | fill-maskFill Mask | CodeCode Available | 2 |
