Model Architecture

Sub-Sequential Physics-Informed Learning with State Space Model ICML 2025 SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation CVPR 2025 Superpose Task-specific Features for Model Merging EMNLP 2025 Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resection with Pringle Maneuver AAAI 2025 SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models ICLR 2025 Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks AISTATS 2025 SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning ICLR 2025 TableKV: KV Cache Compression for In-Context Table Processing ACL 2025 Talent: A Tabular Analytics and Learning Toolbox JMLR 2025 Taming LLMs with Gradient Grouping ACL 2025 Taming Teacher Forcing for Masked Autoregressive Video Generation CVPR 2025 Task-driven Image Fusion with Learnable Fusion Loss CVPR 2025 Task-driven Layerwise Additive Activation Intervention NAACL 2025 Task Vector Quantization for Memory-Efficient Model Merging ICCV 2025 TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation EMNLP 2025 Temperature in Cosine-based Softmax Loss ICCV 2025 TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval ICLR 2025 Temporal Action Detection Model Compression by Progressive Block Drop CVPR 2025 Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation ICLR 2025 TexTailor: Customized Text-aligned Texturing via Effective Resampling ICLR 2025 \textttconfopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods AutoML 2025 Texture Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection WACV 2025 The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference ICML 2025 Theory, Analysis, and Best Practices for Sigmoid Self-Attention ICLR 2025 The Source Image is the Best Attention for Infrared and Visible Image Fusion ICCV 2025