network pruning

Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models CVPR 2026 Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models CVPR 2026 NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices CVPR 2026 Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport CVPR 2026 Achieving Lightweight Super-Resolution for Real-Time Computer Graphics AAAI 2025 GliaNet: Adaptive Neural Network Structure Learning with Glia-Driven CVPR 2025 Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models ACL 2025 ICP: Immediate Compensation Pruning for Mid-to-high Sparsity CVPR 2025 Improving Generalization in Meta-Learning via Meta-Gradient Augmentation IJCAI 2025 Mask in the Mirror: Implicit Sparsification ICLR 2025 MDP: Multidimensional Vision Model Pruning with Latency Constraint CVPR 2025 On-Device Diffusion Transformer Policy for Efficient Robot Manipulation ICCV 2025 On Pruning State-Space LLMs EMNLP 2025 Sparse Structure Exploration and Re-optimization for Vision Transformer UAI 2025 Streamlining Redundant Layers to Compress Large Language Models ICLR 2025 Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers. AAAI 2025 Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective AAAI 2025 Adaptive Sharpness-Aware Pruning for Robust Sparse Networks ICLR 2024 AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking NeurIPS 2024 A Simple and Effective Pruning Approach for Large Language Models ICLR 2024 Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch CVPR 2024 Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers NeurIPS 2024 Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks NAACL 2024 Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs ICLR 2024 Efficient CNNs with Quaternion Transformations and Pruning for Audio Tagging Interspeech 2024