model pruning

The Impact of Inference Acceleration on Bias of LLMs NAACL 2025 ThinkSLM: Towards Reasoning in Small Language Models EMNLP 2025 Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers. AAAI 2025 TinySubNets: An Efficient and Low Capacity Continual Learning Strategy AAAI 2025 Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs EMNLP 2025 Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency EMNLP 2025 Wanda++: Pruning Large Language Models via Regional Gradients ACL 2025 You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning ICLR 2025 Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment NeurIPS 2024 AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models NeurIPS 2024 AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking NeurIPS 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 Balancing Act: Constraining Disparate Impact in Sparse Models ICLR 2024 BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation ICLR 2024 CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection CVPR 2024 Compact Language Models via Pruning and Knowledge Distillation NeurIPS 2024 Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold AAAI 2024 DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices NeurIPS 2024 Data-independent Module-aware Pruning for Hierarchical Vision Transformers ICLR 2024 Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks COLING 2024 DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training ICLR 2024 DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism NeurIPS 2024 DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization NeurIPS 2024 Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization NAACL 2024 Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition Interspeech 2024