← Techniques
Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration AAAI 2025
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem EMNLP 2025
Taming Teacher Forcing for Masked Autoregressive Video Generation CVPR 2025
Binary Event-Driven Spiking Transformer IJCAI 2025
Gradient-Guided Annealing for Domain Generalization CVPR 2025
DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers CVPR 2025
A Centrality-based Graph Learning Framework IJCAI 2025
Event-based Video Super-Resolution via State Space Models CVPR 2025
Multispectral Demosaicing via Dual Cameras ICCV 2025
ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025
SEP: A General Lossless Compression Framework with Semantics Enhancement and Multi-Stream Pipelines IJCAI 2025
One-Step Specular Highlight Removal with Adapted Diffusion Models ICCV 2025
Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration CVPR 2025
NAAST-GNN: Neighborhood Adaptive Aggregation and Spectral Tuning for Graph Anomaly Detection IJCAI 2025
SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting ICCV 2025
Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations ICCV 2025
EDM: Efficient Deep Feature Matching ICCV 2025
CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy ICCV 2025
Efficient Dynamic Graphs Learning with Refined Batch Parallel Training IJCAI 2025
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection ICCV 2025
UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale ICCV 2025
Efficient Concertormer for Image Deblurring and Beyond ICCV 2025
Representation Shift: Unifying Token Compression with FlashAttention ICCV 2025
Scaling Action Detection: AdaTAD++ with Transformer-Enhanced Temporal-Spatial Adaptation ICCV 2025
MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance ICCV 2025