Model Architecture

Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks WACV 2025 PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models CVPR 2025 Perceptual Video Compression with Neural Wrapping CVPR 2025 Perspective-Aware Teaching: Adapting Knowledge for Heterogeneous Distillation ICCV 2025 PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint IJCNLP 2025 Physics-Informed Diffusion Models ICLR 2025 PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations ICLR 2025 Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection AAAI 2025 Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning CVPR 2025 PipeThreader: Software-Defined Pipelining for Efficient DNN Execution OSDI 2025 Pix2Poly: A Sequence Prediction Method for End-to-End Polygonal Building Footprint Extraction from Remote Sensing Imagery WACV 2025 Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach CVPR 2025 Plastic Learning with Deep Fourier Features ICLR 2025 PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts NAACL 2025 Plug-and-Play Tri-Branch Invertible Block for Image Rescaling AAAI 2025 PolaFormer: Polarity-aware Linear Attention for Vision Transformers ICLR 2025 Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters AAAI 2025 Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks ICLR 2025 PRDP: Progressively Refined Differentiable Physics ICLR 2025 Predicting the Susceptibility of Examples to Catastrophic Forgetting ICML 2025 Primphormer: Efficient Graph Transformers with Primal Representations ICML 2025 Proactive Hearing Assistants that Isolate Egocentric Conversations EMNLP 2025 Prostate Cancer Detection in Bi-Parametric MRI using Zonal Anatomy-Guided U-Mamba with Multi-Task Learning MIDL 2025 Prototype Guided Backdoor Defense via Activation Space Manipulation ICCV 2025 Pruning for GNNs: Lower Complexity with Comparable Expressiveness ICML 2025