Model Compression

Glyph: Scaling Context Windows via Visual-Text Compression ACL 2026 Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution CVPR 2026 GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting CVPR 2026 Hi-Lo Prune: Look at What You'll Lose before Pruning with Hierarchical Token Selection CVPR 2026 HiSVD: Principled Low-Rank Approximation of LLMs via Hierarchical Modeling of Information Capacity and Spectral Structure ACL 2026 IMPACT: Importance-Aware Activation Space Reconstruction ACL 2026 JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression ACL 2026 Layered 4D-Rotor Gaussian Splatting: A Compressed Representation for Long Dynamic Scenes CVPR 2026 Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models ACL 2026 LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference ACL 2026 Learning Differentiable Hierarchies in 3D Gaussian Splatting CVPR 2026 Learning Quantized Continuous Controllers for Integer Hardware L4DC 2026 LightRR: A Lightweight Network for Single Image Reflection Removal CVPR 2026 Logit-Margin Repulsion for Backdoor Defense CVPR 2026 LS-ViT: Least-Squares Hessian Based Block Reconstruction for Low-Bit Post-Training Quantization of Vision Transformers CVPR 2026 Making Large Language Models Efficient Dense Retrievers ACL 2026 Mapping Networks CVPR 2026 Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation CVPR 2026 MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning ACL 2026 MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning CVPR 2026 Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models CVPR 2026 Motivating Next-Gen Accelerators with Flexible N:M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches ACL 2026 MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering CVPR 2026 Neural Differentiation in Deep Networks: A Theoretical Framework for Expressivity and Representational Diversity CVPR 2026 Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation ACL 2026