Model Compression

Graph Sparsification via Mixture of Graphs ICLR 2025 GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression EMNLP 2025 Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free ACL 2025 Growing a Twig to Accelerate Large Vision-Language Models ICCV 2025 GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning ACL 2025 HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS ICLR 2025 Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference EMNLP 2025 Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models ACL 2025 HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem NAACL 2025 HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models ICLR 2025 HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models AAAI 2025 HookMoE: A learnable performance compensation strategy of Mixture-of-Experts for LLM inference acceleration EMNLP 2025 Hopscotch: Discovering and Skipping Redundancies in Language Models EMNLP 2025 H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models ICML 2025 Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations EMNLP 2025 HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging EMNLP 2025 HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis CVPR 2025 Hypernetworks for Perspectivist Adaptation EMNLP 2025 IAM: Efficient Inference through Attention Mapping between Different-scale LLMs ACL 2025 ICP: Immediate Compensation Pruning for Mid-to-high Sparsity CVPR 2025 IG-Pruning: Input-Guided Block Pruning for Large Language Models EMNLP 2025 ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs ACL 2025 Improved Sparse Upcycling for Instruction Tuning COLING 2025 Improving Efficiency in Large Language Models via Extendable Block Floating Point Representation ACL 2025 Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency ICLR 2025