Model Compression

LightFormer: Light-weight Transformer Using SVD-based Weight Transfer and Parameter Sharing ACL 2023 LOFT: Finding Lottery Tickets through Filter-wise Training AISTATS 2023 LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation ICML 2023 Lossless 4-bit Quantization of Architecture Compressed Conformer ASR Systems on the 300-hr Switchboard Corpus Interspeech 2023 Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost AAAI 2023 Making Vision Transformers Efficient From a Token Sparsification View CVPR 2023 MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization EMNLP 2023 Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack NeurIPS 2023 MARS: Masked Automatic Ranks Selection in Tensor Decompositions AISTATS 2023 Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models ACL 2023 MEDIC: Remove Model Backdoors via Importance Driven Cloning CVPR 2023 Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization NeurIPS 2023 Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis CVPR 2023 Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training ACL 2023 MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering CVPR 2023 Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models’ Memories ACL 2023 Mixture-of-Expert Conformer for Streaming Multilingual ASR Interspeech 2023 Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models EMNLP 2023 MobileOne: An Improved One Millisecond Mobile Backbone CVPR 2023 MobileTL: On-Device Transfer Learning with Inverted Residual Blocks AAAI 2023 Moccasin: Efficient Tensor Rematerialization for Neural Networks ICML 2023 Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection CVPR 2023 Model Compression for DNN-based Speaker Verification Using Weight Quantization Interspeech 2023 Model Shapley: Equitable Model Valuation with Black-box Access NeurIPS 2023 Model Sparsity Can Simplify Machine Unlearning NeurIPS 2023