← Techniques
Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

EA-KD: Entropy-based Adaptive Knowledge Distillation ICCV 2025
One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images ICCV 2025
Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning ICCV 2025
Addressing Representation Collapse in Vector Quantized Models with One Linear Layer ICCV 2025
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics ICCV 2025
Towards a Universal Image Degradation Model via Content-Degradation Disentanglement ICCV 2025
Temperature in Cosine-based Softmax Loss ICCV 2025
Frequency-Biased Synergistic Design for Image Compression and Compensation CVPR 2025
Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification AAAI 2025
Decoupling Training-Free Guided Diffusion by ADMM CVPR 2025
TKG-DM: Training-free Chroma Key Content Generation Diffusion Model CVPR 2025
SACB-Net: Spatial-awareness Convolutions for Medical Image Registration CVPR 2025
SerialGen: Personalized Image Generation by First Standardization Then Personalization CVPR 2025
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability CVPR 2025
CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation AAAI 2025
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering CVPR 2025
SAM Decoding: Speculative Decoding via Suffix Automaton ACL 2025
Retrofitting Large Language Models with Dynamic Tokenization ACL 2025
Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction CVPR 2025
PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction CVPR 2025
GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation CVPR 2025
AniGrad: Anisotropic Gradient-Adaptive Sampling for 3D Reconstruction From Monocular Video CVPR 2025
ROICtrl: Boosting Instance Control for Visual Generation CVPR 2025
Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising CVPR 2025
BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment ICCV 2025