Transformers

Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling NeurIPS 2024 Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift ICLR 2024 Understanding the Training Speedup from Sampling with Approximate Losses ICML 2024 Understanding Transformer Reasoning Capabilities via Graph Algorithms NeurIPS 2024 Uni3D: Exploring Unified 3D Representation at Scale ICLR 2024 UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation EMNLP 2024 Unified Generative and Discriminative Training for Multi-modal Large Language Models NeurIPS 2024 Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action CVPR 2024 Unified Lexical Representation for Interpretable Visual-Language Alignment NeurIPS 2024 Unified Multi-Talker ASR with and without Target-speaker Enrollment Interspeech 2024 Unified Training of Universal Time Series Forecasting Transformers ICML 2024 Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence ICLR 2024 Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval COLING 2024 Unifying Visual and Vision-Language Tracking via Contrastive Learning AAAI 2024 UniIF: Unified Molecule Inverse Folding NeurIPS 2024 UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion ACL 2024 UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization CVPR 2024 UniTS: A Unified Multi-Task Time Series Model NeurIPS 2024 UNIT: Unifying Image and Text Recognition in One Vision Encoder NeurIPS 2024 Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators NeurIPS 2024 UniVS: Unified and Universal Video Segmentation with Prompts as Queries CVPR 2024 Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation ICLR 2024 Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding CVPR 2024 Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models EMNLP 2024 Unleashing the Power of Discourse-Enhanced Transformers for Propaganda Detection EACL 2024