Model Compression

Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution CVPR 2025 Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation ACL 2025 Advancing Weight and Channel Sparsification with Enhanced Saliency WACV 2025 Adversarial Diffusion Compression for Real-World Image Super-Resolution CVPR 2025 A Good Teacher Adapts Their Knowledge for Distillation ICCV 2025 AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model ICCV 2025 AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025 AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers AAAI 2025 AIRA: Activation-Informed Low-Rank Adaptation for Large Models ICCV 2025 Aligning Sizes of Intermediate Layers by LoRA Adapter for Knowledge Distillation NAACL 2025 A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality EMNLP 2025 AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization WACV 2025 APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers CVPR 2025 A Pipeline to Assess Merging Methods via Behavior and Internals EMNLP 2025 Archaeology at TSAR 2025 Shared Task Teaching Small Models to do CEFR Simplifications EMNLP 2025 Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? CVPR 2025 As easy as PIE: understanding when pruning causes language models to disagree NAACL 2025 ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization AAAI 2025 Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition ACL 2025 Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration CVPR 2025 Automated Fine-Grained Mixture-of-Experts Quantization ACL 2025 Avoiding Copyright Infringement via Large Language Model Unlearning NAACL 2025 BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training ICML 2025 Basic Reading Distillation ACL 2025 BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios ACL 2025