Model Compression

Unlocking the Potential of Lightweight Quantized Models for Deepfake Detection IJCAI 2025 UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models ACL 2025 Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging ACL 2025 Value Residual Learning ACL 2025 VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting AAAI 2025 Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs ACL 2025 VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping AAAI 2025 Vicomtech@WMT 2025: Evolutionary Model Compression for Machine Translation EMNLP 2025 ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025 Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective AAAI 2025 ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models ICCV 2025 Vocabulary-level Memory Efficiency for Language Model Fine-tuning NAACL 2025 VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers AAAI 2025 Wanda++: Pruning Large Language Models via Regional Gradients ACL 2025 WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models CVPR 2025 Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models EMNLP 2025 Weights-Rotated Preference Optimization for Large Language Models EMNLP 2025 WINS: Winograd Structured Pruning for Fast Winograd Convolution ICCV 2025 XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression EMNLP 2025 ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity ICCV 2025 $C^2M^3$: Cycle-Consistent Multi-Model Merging NeurIPS 2024 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution NeurIPS 2024 3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability NeurIPS 2024 4K-Resolution Photo Exposure Correction at 125 FPS With ~8K Parameters WACV 2024 A Bayesian Approach to Data Point Selection NeurIPS 2024