Model Compression

PARA: Parameter-Efficient Fine-tuning with Prompt-Aware Representation Adjustment EMNLP 2024 ParsNets: A Parsimonious Composition of Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning IJCAI 2024 PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks WACV 2024 PB-LLM: Partially Binarized Large Language Models ICLR 2024 PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models NAACL 2024 PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs ACL 2024 Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models ICLR 2024 Plug-and-Play Diffusion Distillation CVPR 2024 PMET: Precise Model Editing in a Transformer AAAI 2024 PolyuCBS at SMM4H 2024: LLM-based Medical Disorder and Adverse Drug Event Detection with Low-rank Adaptation ACL 2024 Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model EMNLP 2024 Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization EMNLP 2024 PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation EACL 2024 PrivCirNet: Efficient Private Inference via Block Circulant Transformation NeurIPS 2024 Probabilistically Robust Watermarking of Neural Networks IJCAI 2024 Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models COLING 2024 PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning NAACL 2024 PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning EMNLP 2024 Protecting Your LLMs with Information Bottleneck NeurIPS 2024 Pruning as a Domain-specific LLM Extractor NAACL 2024 Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models COLING 2024 Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning EMNLP 2024 Pruning Foundation Models for High Accuracy without Retraining EMNLP 2024 Pruning From Scratch via Shared Pruning Module and Nuclear Norm-Based Regularization WACV 2024 Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations ACL 2024