model architecture

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network CVPR 2025 ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance IJCNLP 2025 ModRWKV: Transformer Multimodality in Linear Time EMNLP 2025 MossNet: Mixture of State-Space Experts is a Multi-Head Attention IJCNLP 2025 OPTICAL: Leveraging Optimal Transport for Contribution Allocation in Dataset Distillation CVPR 2025 ParZC: Parametric Zero-Cost Proxies for Efficient NAS AAAI 2025 Perceptual Video Compression with Neural Wrapping CVPR 2025 Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research EMNLP 2025 PowerMLP: An Efficient Version of KAN AAAI 2025 Revealing and Mitigating the Local Pattern Shortcuts of Mamba ACL 2025 Scaling Inference-Efficient Language Models ICML 2025 SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks AAAI 2025 SpiralMLP: A Lightweight Vision MLP Architecture WACV 2025 StitchLLM: Serving LLMs, One Block at a Time ACL 2025 Talent: A Tabular Analytics and Learning Toolbox JMLR 2025 Temporally Streaming Audio-Visual Synchronization for Real-World Videos WACV 2025 TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba ICCV 2025 Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights CVPR 2025 Transformers without Normalization CVPR 2025 TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025 Trusted Multi-View Classification via Evolutionary Multi-View Fusion ICLR 2025 Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers WACV 2025 Your ViT is Secretly an Image Segmentation Model CVPR 2025 A Benchmark Study on Calibration ICLR 2024 AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation NeurIPS 2024