Transformers

D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection ICCV 2025 DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Images ICCV 2025 DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing ICCV 2025 DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning ACL 2025 DAPE V2: Process Attention Score as Feature Map for Length Extrapolation ACL 2025 DarSwin-Unet: Distortion Aware Architecture WACV 2025 Data or Language Supervision: What Makes CLIP Better than DINO? EMNLP 2025 DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers CVPR 2025 DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer ICCV 2025 DCTMamba: Advancing JPEG Image Restoration Through Long-Sequence Modeling and Adaptive Frequency Strategy AAAI 2025 De^2Gaze: Deformable and Decoupled Representation Learning for 3D Gaze Estimation CVPR 2025 DeciMamba: Exploring the Length Extrapolation Potential of Mamba ICLR 2025 Decision SpikeFormer: Spike-Driven Transformer for Decision Making CVPR 2025 Decoder-Only LLMs can be Masked Auto-Encoders ACL 2025 Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025 Decomposed Spatio-Temporal Mamba for Long-Term Traffic Prediction AAAI 2025 Decomposition of Graphic Design with Unified Multimodal Model ICML 2025 Deconstructing Attention: Investigating Design Principles for Effective Language Modeling IJCNLP 2025 Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer ICCV 2025 Decoupled Motion Expression Video Segmentation CVPR 2025 DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classification EMNLP 2025 Deep-change at CoMeDi: the Cross-Entropy Loss is not All You Need COLING 2025 Deep Generative Model for Mechanical System Configuration Design AAAI 2025 Deep Hierarchies and Invariant Disease-Indicative Feature Learning for Computer Aided Diagnosis of Multiple Fundus Diseases AAAI 2025 Deeply Supervised Flow-Based Generative Models ICCV 2025