Model Compression

NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices CVPR 2026 OCP: Outlier-Centric Probing for Dynamic Structured Pruning of LLMs ACL 2026 One-Cycle Structured Pruning via Stability-Driven Subnetwork Search WACV 2026 One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs CVPR 2026 PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference ACL 2026 PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models ACL 2026 Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers CVPR 2026 Post-training Feature Pruning for Fundus Images Classification CVPR 2026 Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation ACL 2026 Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving CVPR 2026 PVeRA: Probabilistic Vector-Based Random Matrix Adaptation WACV 2026 QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models CVPR 2026 Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression ACL 2026 QuietPrune: Query-Guided Early Token Pruning for Vision-Language Models CVPR 2026 QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer CVPR 2026 Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods ACL 2026 Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression ACL 2026 Rethinking Asymmetric Quantization: Hidden Symmetry in Vision Model Weights CVPR 2026 S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations CVPR 2026 Sampling-Aware Quantization for Diffusion Models CVPR 2026 SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models CVPR 2026 Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification ACL 2026 Theoretical Compression Bounds for Wide Multilayer Perceptrons COLT 2026 TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model CVPR 2026 TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies CVPR 2026