Transformers

Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation CVPR 2025 Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection ICCV 2025 Synthetic Singers: A Review of Deep-Learning-based Singing Voice Synthesis Approaches IJCNLP 2025 TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation ICLR 2025 TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization AAAI 2025 TabICL: A Tabular Foundation Model for In-Context Learning on Large Data ICML 2025 TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular Data ICML 2025 TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models ICCV 2025 TaCL-CoMoE: Task-adaptive Contrastive Learning with Cooperative Mixture of Experts for Multi-task Social Media Analysis IJCNLP 2025 TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering ACL 2025 TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition AAAI 2025 Taming Transformer Without Using Learning Rate Warmup ICLR 2025 TAM-VT: Transformation-Aware Multi-Scale Video Transformer for Segmentation and Tracking WACV 2025 TAPNext: Tracking Any Point (TAP) as Next Token Prediction ICCV 2025 TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction ICCV 2025 Target Bias Is All You Need: Zero-Shot Debiasing of Vision-Language Models with Bias Corpus ICCV 2025 Target Return Optimizer for Multi-Game Decision Transformer ACML 2025 TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis ICCV 2025 TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval SemEval 2025 Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting CVPR 2025 TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances AAAI 2025 TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation AAAI 2025 TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis ACL 2025 Team Horizon at BHASHA Task 1: Multilingual IndicGEC with Transformer-based Grammatical Error Correction Models AACL 2025 Team Horizon at BHASHA Task 2: Fine-tuning Multilingual Transformers for Indic Word Grouping AACL 2025