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

Model Compression

1,785 papers

Papers per year

7
197
419
'15
'20
'25

Papers

UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers ICML 2023
MODeL: Memory Optimizations for Deep Learning ICML 2023
Private Federated Learning with Autotuned Compression ICML 2023
UPSCALE: Unconstrained Channel Pruning ICML 2023
DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023
Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases ICML 2023
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models ICML 2023
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models ICML 2023
Traversing Between Modes in Function Space for Fast Ensembling ICML 2023
Bi-directional Masks for Efficient N:M Sparse Training ICML 2023
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch ICML 2023
Calibrating a Deep Neural Network with Its Predecessors IJCAI 2023
Towards Fully Quantized Neural Networks For Speech Enhancement INTERSPEECH 2023
Accelerating Transducers through Adjacent Token Merging INTERSPEECH 2023
A Binary Keyword Spotting System with Error-Diffusion Based Feature Binarization INTERSPEECH 2023
An Efficient and Noise-Robust Audiovisual Encoder for Audiovisual Speech Recognition INTERSPEECH 2023
SparseVSR: Lightweight and Noise Robust Visual Speech Recognition INTERSPEECH 2023
Model Compression for DNN-based Speaker Verification Using Weight Quantization INTERSPEECH 2023
EffCRN: An Efficient Convolutional Recurrent Network for High-Performance Speech Enhancement INTERSPEECH 2023
Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression INTERSPEECH 2023
A Multiple-Teacher Pruning Based Self-Distillation (MT-PSD) Approach to Model Compression for Audio-Visual Wake Word Spotting INTERSPEECH 2023
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization INTERSPEECH 2023
miniStreamer: Enhancing Small Conformer with Chunked-Context Masking for Streaming ASR Applications on the Edge INTERSPEECH 2023
CoMFLP: Correlation Measure Based Fast Search on ASR Layer Pruning INTERSPEECH 2023
Lossless 4-bit Quantization of Architecture Compressed Conformer ASR Systems on the 300-hr Switchboard Corpus INTERSPEECH 2023