← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Boost Embodied AI Models with Robust Compression Boundary IJCAI 2025
FBQuant: FeedBack Quantization for Large Language Models IJCAI 2025
TreeKV: Smooth Key-Value Cache Compression with Tree Structures IJCAI 2025
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant IJCAI 2025
Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information IJCAI 2025
Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors IJCAI 2025
Federated Low-Rank Adaptation for Foundation Models: A Survey IJCAI 2025
AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model ICCV 2025
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025
Less is More: Empowering GUI Agent with Context-Aware Simplification ICCV 2025
Knowledge Distillation for Learned Image Compression ICCV 2025
EA-KD: Entropy-based Adaptive Knowledge Distillation ICCV 2025
ICP: Immediate Compensation Pruning for Mid-to-high Sparsity CVPR 2025
Inference-Time Diffusion Model Distillation ICCV 2025
TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025
Importance-Based Token Merging for Efficient Image and Video Generation ICCV 2025
Efficient Neural Network Encoding for 3D Color Lookup Tables AAAI 2025
Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration ICCV 2025
Outlier-Aware Post-Training Quantization for Image Super-Resolution ICCV 2025
Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation AAAI 2025
Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025
ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models ICCV 2025
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity AAAI 2025
TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning ICCV 2025
FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures AAAI 2025