Model Architecture

ShiftwiseConv: Small Convolutional Kernel with Large Kernel Effect CVPR 2025 Simplification Is All You Need against Out-of-Distribution Overconfidence CVPR 2025 Slice-and-Pack: Tailoring Deep Models for Customized Requirements AAAI 2025 SliderSpace: Decomposing the Visual Capabilities of Diffusion Models ICCV 2025 SLlama: Parameter-Efficient Language Model Architecture for Enhanced Linguistic Competence Under Strict Data Constraints EMNLP 2025 SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning ICCV 2025 Sparse Fine-Tuning of Transformers for Generative Tasks ICCV 2025 SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks AAAI 2025 Spatial Alignment and Temporal Matching Adapter for Video-Radar Remote Physiological Measurement ICCV 2025 SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion ICCV 2025 Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling CVPR 2025 Spectral Image Tokenizer ICCV 2025 Spectro-Riemannian Graph Neural Networks ICLR 2025 SpeechHGT: A Multimodal Hypergraph Transformer for Speech-Based Early Alzheimer’s Disease Detection IJCAI 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 SpiralMLP: A Lightweight Vision MLP Architecture WACV 2025 SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking CVPR 2025 SSLFusion: Scale and Space Aligned Latent Fusion Model for Multimodal 3D Object Detection AAAI 2025 SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting ICCV 2025 Stable Segment Anything Model ICLR 2025 STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation ACL 2025 Star with Bilinear Mapping CVPR 2025 Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025 Structural Deep Encoding for Table Question Answering ACL 2025 Structure Modeling Approach for UD Parsing of Historical Modern Japanese ACL 2025