Model Compression

DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing WACV 2025 DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers ICCV 2025 DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025 DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization ICCV 2025 Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study EMNLP 2025 Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models EMNLP 2025 Do We Really Need All Those Dimensions? An Intrinsic Evaluation Framework for Compressed Embeddings EMNLP 2025 Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs EMNLP 2025 DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization ACL 2025 DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025 Dual Information Purification for Lightweight SAR Object Detection AAAI 2025 DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models CVPR 2025 DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception WACV 2025 EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models ACL 2025 EA-KD: Entropy-based Adaptive Knowledge Distillation ICCV 2025 ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training EMNLP 2025 Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning CVPR 2025 Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks CVPR 2025 Efficient Diffusion as Low Light Enhancer CVPR 2025 Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation ICCV 2025 Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation ICCV 2025 EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models CVPR 2025 Efficient Neural Network Encoding for 3D Color Lookup Tables AAAI 2025 Efficient On-Device Text Simplification for Firefox with Synthetic Data Fine-Tuning EMNLP 2025 EfficientQAT: Efficient Quantization-Aware Training for Large Language Models ACL 2025