conftrace_
← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1,785 papers

Papers per year

7
197
419
'15
'20
'25

Papers

Compressed MoE ASR Model Based on Knowledge Distillation and Quantization INTERSPEECH 2023
Information Magnitude Based Dynamic Sub-sampling for Speech-to-text INTERSPEECH 2023
LightClone: Speaker-guided Parallel Subnet Selection for Few-shot Voice Cloning INTERSPEECH 2023
2-bit Conformer quantization for automatic speech recognition INTERSPEECH 2023
Adaptive Neural Network Quantization For Lightweight Speaker Verification INTERSPEECH 2023
Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint JMLR 2023
Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge NSDI 2023
Efficient Skeleton-Based Action Recognition via Joint-Mapping Strategies WACV 2023
FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-Off Between Accuracy and Robustness WACV 2023
Spartan: Differentiable Sparsity via Regularized Transportation NIPS 2022
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning NIPS 2022
Discovering and Overcoming Limitations of Noise-engineered Data-free Knowledge Distillation NIPS 2022
BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons NIPS 2022
Leveraging Inter-Layer Dependency for Post -Training Quantization NIPS 2022
Towards Disentangling Information Paths with Coded ResNeXt NIPS 2022
Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation NIPS 2022
Dataset Distillation using Neural Feature Regression NIPS 2022
Sparse Structure Search for Delta Tuning NIPS 2022
Parameter-Efficient Masking Networks NIPS 2022
Symbolic Distillation for Learned TCP Congestion Control NIPS 2022
Structural Pruning via Latency-Saliency Knapsack NIPS 2022
VTC-LFC: Vision Transformer Compression with Low-Frequency Components NIPS 2022
Deep Compression of Pre-trained Transformer Models NIPS 2022
BiT: Robustly Binarized Multi-distilled Transformer NIPS 2022
projUNN: efficient method for training deep networks with unitary matrices NIPS 2022