← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Binary Event-Driven Spiking Transformer IJCAI 2025
SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models WACV 2025
Boost Embodied AI Models with Robust Compression Boundary IJCAI 2025
FBQuant: FeedBack Quantization for Large Language Models IJCAI 2025
WINS: Winograd Structured Pruning for Fast Winograd Convolution ICCV 2025
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding NAACL 2025
RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model NAACL 2025
As easy as PIE: understanding when pruning causes language models to disagree NAACL 2025
Large Language Models Are Overparameterized Text Encoders NAACL 2025
Vocabulary-level Memory Efficiency for Language Model Fine-tuning NAACL 2025
Encoder-Aware Sequence-Level Knowledge Distillation for Low-Resource Neural Machine Translation NAACL 2025
Outlier-Aware Post-Training Quantization for Image Super-Resolution ICCV 2025
CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis AAAI 2025
TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration WACV 2025
ICP: Immediate Compensation Pruning for Mid-to-high Sparsity CVPR 2025
Unlocking the Potential of Lightweight Quantized Models for Deepfake Detection IJCAI 2025
Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025
EnergyCompress: A General Case Base Learning Strategy IJCAI 2025
Not All Layers of LLMs Are Necessary During Inference IJCAI 2025
DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception WACV 2025
Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks WACV 2025
Comparative Knowledge Distillation WACV 2025
ELMGS: Enhancing Memory and Computation Scalability through Compression for 3D Gaussian Splatting WACV 2025
Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation WACV 2025
Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels ICCV 2025