model compression

Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025 Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding EMNLP 2025 Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models EMNLP 2025 Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models ICLR 2025 Treasures in Discarded Weights for LLM Quantization AAAI 2025 TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs ACL 2025 TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025 TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning ICCV 2025 Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis ICCV 2025 Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization ICLR 2025 UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective EMNLP 2025 Understanding and Improving Information Preservation in Prompt Compression for LLMs EMNLP 2025 Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models Interspeech 2025 Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language Models EMNLP 2025 Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models ACL 2025 UNLEARN Efficient Removal of Knowledge in Large Language Models NAACL 2025 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 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 Variance-Based Pruning for Accelerating and Compressing Trained Networks ICCV 2025 VeriFastScore: Speeding up long-form factuality evaluation EMNLP 2025 Vicomtech@WMT 2025: Evolutionary Model Compression for Machine Translation EMNLP 2025 ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025