An efficient blur kernel estimation method for blind image Super-Resolution

You only compress once: Towards effective and elastic BERT compression via exploit-explore stochastic nature gradient

ARLP: Automatic multi-agent transformer reinforcement learning pruner for one-shot neural network pruning

Deep hybrid transformer network for robust modulation classification in wireless communications

MOVE AND ACT: ENHANCED OBJECT MANIPULATION AND BACKGROUND INTEGRITY FOR IMAGE EDITING

Optg: Optimizing Gradient-Driven Criteria in Network Sparsity

Actor-Critic With Synthesis Loss for Solving Approximation Biases

ConCLVD: Controllable Chinese Landscape Video Generation via Diffusion Model

Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization

Local representation-based neighbourhood for robust classification

Learning Image Demoiréing from Unpaired Real Data

AFFINEQUANT: AFFINE TRANSFORMATION QUANTIZATION FOR LARGE LANGUAGE MODELS

Multi-scale representation of surface-enhanced Raman spectroscopy data for deep learning-based liver cancer detection

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs

An Efficient Blur Kernel Estimation Method for Blind Image Super-Resolution

Shadow-aware dynamic convolution for shadow removal

Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration

Learning Image Demoiréing from Unpaired Real Data

Enhancing GAN Compression by Image Probability Distribution Distillation

Binarizing Super-Resolution Neural Network Without Batch Normalization

Frequency Domain Distillation for Data-Free Quantization of Vision Transformer

Dynamic Neural Networks for Adaptive Implicit Image Compression

Large Kernel Convolutional Attention Based U-Net Network for Inpainting Oracle Bone Inscription

Uncovering the Over-Smoothing Challenge in Image Super-Resolution: Entropy-Based Quantification and Contrastive Optimization

FUNCTIONALLY SIMILAR MULTI-LABEL KNOWLEDGE DISTILLATION

AFFINEQUANT: AFFINE TRANSFORMATION QUANTIZATION FOR LARGE LANGUAGE MODELS