Model Compression

On Pruning State-Space LLMs EMNLP 2025 On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models ICLR 2025 On the Relation between Trainability and Dequantization of Variational Quantum Learning Models ICLR 2025 Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization ACL 2025 Optimizing Neural Network Representations of Boolean Networks ICLR 2025 OptiPrune: Effective Pruning Approach for Every Target Sparsity COLING 2025 OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting ICLR 2025 Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion Models ICML 2025 Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models ACL 2025 P2 Law: Scaling Law for Post-Training After Model Pruning ACL 2025 PaCA: Partial Connection Adaptation for Efficient Fine-Tuning ICLR 2025 PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models CVPR 2025 PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS ICLR 2025 Palu: KV-Cache Compression with Low-Rank Projection ICLR 2025 Parameter and Memory Efficient Pretraining via Low-rank Riemannian Optimization ICLR 2025 Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace COLING 2025 PARQ: Piecewise-Affine Regularized Quantization ICML 2025 Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP WACV 2025 PAT: Pruning-Aware Tuning for Large Language Models AAAI 2025 PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models EMNLP 2025 PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint IJCNLP 2025 Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning CVPR 2025 PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding ACL 2025 PipeThreader: Software-Defined Pipelining for Efficient DNN Execution OSDI 2025 PIP: Perturbation-based Iterative Pruning for Large Language Models EMNLP 2025