Model Compression

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay ICCV 2025 Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding ACL 2025 Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency ACL 2025 Position: Enough of Scaling LLMs! Lets Focus on Downscaling ICML 2025 Power doesn’t reside in size: A Low Parameter Hybrid Language Model (HLM) for Sentiment Analysis in Code-mixed data EMNLP 2025 PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation EMNLP 2025 Practical Offloading for Fine-Tuning LLM on Commodity GPU via Learned Sparse Projectors AAAI 2025 Pre-Trained Multiple Latent Variable Generative Models are Good Defenders Against Adversarial Attacks WACV 2025 Pretraining Context Compressor for Large Language Models with Embedding-Based Memory ACL 2025 Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models ACL 2025 PrivDNFIS: Privacy-preserving and Efficient Deep Neuro-Fuzzy Inference System AAAI 2025 Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation ICLR 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing ICLR 2025 ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations ACL 2025 ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025 Prompt Compression for Large Language Models: A Survey NAACL 2025 Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025 ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models COLING 2025 PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality EMNLP 2025 PruneSLU: Efficient On-device Spoken Language Understanding through Vocabulary and Structural Pruning Interspeech 2025 Pruning General Large Language Models into Customized Expert Models ACL 2025 Pruning Large Language Models with Semi-Structural Adaptive Sparse Training AAAI 2025 Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge WACV 2025 Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs EMNLP 2025