Transformers

MinSpeech: A Corpus of Southern Min Dialect for Automatic Speech Recognition Interspeech 2024 MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning Interspeech 2024 Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities CVPR 2024 MIST: Medical Image Segmentation Transformer With Convolutional Attention Mixing (CAM) Decoder WACV 2024 Mitigating Object Hallucination via Concentric Causal Attention NeurIPS 2024 Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion AAAI 2024 Mixing and Matching: Combining Independently Trained Translation Model Components EACL 2024 Mixture of Experts Meets Prompt-Based Continual Learning NeurIPS 2024 Mixture of In-Context Experts Enhance LLMs' Long Context Awareness NeurIPS 2024 Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules EMNLP 2024 Mixture of Nested Experts: Adaptive Processing of Visual Tokens NeurIPS 2024 Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding COLING 2024 Mixture of Tokens: Continuous MoE through Cross-Example Aggregation NeurIPS 2024 MLDSP-MA: Multidimensional Attention for Multi-Round Long Dialogue Sentiment Prediction COLING 2024 MLP Can Be A Good Transformer Learner CVPR 2024 MLP-DINO: Category Modeling and Query Graphing with Deep MLP for Object Detection IJCAI 2024 MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding NeurIPS 2024 MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification EMNLP 2024 MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins NeurIPS 2024 Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers ICML 2024 MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training CVPR 2024 MobileInst: Video Instance Segmentation on the Mobile AAAI 2024 Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera CVPR 2024 MoCha-Stereo: Motif Channel Attention Network for Stereo Matching CVPR 2024 Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction COLING 2024