Transformers

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation NeurIPS 2024 Direct Speech Synthesis from Non-Invasive, Neuromagnetic Signals Interspeech 2024 Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision EACL 2024 Discovering Syntactic Interaction Clues for Human-Object Interaction Detection CVPR 2024 Discriminative Probing and Tuning for Text-to-Image Generation CVPR 2024 Disentangled Prompt Representation for Domain Generalization CVPR 2024 DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models NeurIPS 2024 Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion ICML 2024 Dissecting Query-Key Interaction in Vision Transformers NeurIPS 2024 Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers NeurIPS 2024 Distilling Knowledge from Large-Scale Image Models for Object Detection ECCV 2024 Distinguished In Uniform: Self-Attention Vs. Virtual Nodes ICLR 2024 DiTFastAttn: Attention Compression for Diffusion Transformer Models NeurIPS 2024 DiVAS: Video and Audio Synchronization with Dynamic Frame Rates CVPR 2024 dkit@LT-EDI-2024: Detecting Homophobia and Transphobia in English Social Media Comments EACL 2024 D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models NeurIPS 2024 DLUT and GTCOM’s Neural Machine Translation Systems for WMT24 EMNLP 2024 DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model ICLR 2024 DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes ICLR 2024 DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding EMNLP 2024 DocFormerv2: Local Features for Document Understanding AAAI 2024 DocMSU: A Comprehensive Benchmark for Document-Level Multimodal Sarcasm Understanding AAAI 2024 DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding AAAI 2024 Document Structure in Long Document Transformers EACL 2024 Dodo: Dynamic Contextual Compression for Decoder-only LMs ACL 2024