Model Compression

AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection ACL 2025 Adaptive Dual Guidance Knowledge Distillation AAAI 2025 Adaptive Graph Unlearning IJCAI 2025 Adaptive Length Image Tokenization via Recurrent Allocation ICLR 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 AIRA: Activation-Informed Low-Rank Adaptation for Large Models ICCV 2025 Aligning Sizes of Intermediate Layers by LoRA Adapter for Knowledge Distillation NAACL 2025 Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement CVPR 2025 All You Need in Knowledge Distillation Is a Tailored Coordinate System AAAI 2025 (Almost) Free Modality Stitching of Foundation Models EMNLP 2025 A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality EMNLP 2025 AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models EMNLP 2025 AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting ACL 2025 An Efficient and Accurate Dynamic Sparse Training Framework Based on Parameter-Freezing AAAI 2025 An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation EMNLP 2025 A New Federated Learning Framework Against Gradient Inversion Attacks AAAI 2025 An Orthogonal High-Rank Adaptation for Large Language Models EMNLP 2025 APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers CVPR 2025 A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition ICCV 2025 A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning ICLR 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 A Semantic-Aware Layer-Freezing Approach to Computation-Efficient Fine-Tuning of Language Models ACL 2025 ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization AAAI 2025