← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023
On the Dimensionality of Sentence Embeddings EMNLP 2023
Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules EMNLP 2023
Multilingual Lottery Tickets to Pretrain Language Models EMNLP 2023
The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models EMNLP 2023
FaLA: Fast Linear Adaptation for Replacing Backbone Models on Edge Devices EMNLP 2023
MUX-PLMs: Data Multiplexing for High-throughput Language Models EMNLP 2023
Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023
HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation EMNLP 2023
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer EMNLP 2023
AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation EMNLP 2023
Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing EMNLP 2023
Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval EMNLP 2023
Gradient-based Gradual Pruning for Language-Specific Multilingual Neural Machine Translation EMNLP 2023
Dynamic Low-rank Estimation for Transformer-based Language Models EMNLP 2023
Co-training and Co-distillation for Quality Improvement and Compression of Language Models EMNLP 2023
Dynamic Stashing Quantization for Efficient Transformer Training EMNLP 2023
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models EMNLP 2023
Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression CVPR 2023
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer CVPR 2023
Lossless 4-bit Quantization of Architecture Compressed Conformer ASR Systems on the 300-hr Switchboard Corpus INTERSPEECH 2023
Compressed MoE ASR Model Based on Knowledge Distillation and Quantization INTERSPEECH 2023
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization ICCV 2023
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation ICCV 2023