Model Compression

Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting NeurIPS 2024 Partial Binarization of Neural Networks for Budget-Aware Efficient Learning WACV 2024 PELA: Learning Parameter-Efficient Models with Low-Rank Approximation CVPR 2024 Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale EMNLP 2024 Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts EMNLP 2024 Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NeurIPS 2024 pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning NeurIPS 2024 Pick-or-Mix: Dynamic Channel Sampling for ConvNets CVPR 2024 PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks CVPR 2024 Pipeline Parallelism with Controllable Memory NeurIPS 2024 PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization CVPR 2024 PostMark: A Robust Blackbox Watermark for Large Language Models EMNLP 2024 Practical Hybrid Gradient Compression for Federated Learning Systems IJCAI 2024 Practical Privacy-Preserving MLaaS: When Compressive Sensing Meets Generative Networks AAAI 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 PRewrite: Prompt Rewriting with Reinforcement Learning ACL 2024 Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion AAAI 2024 Progressively Knowledge Distillation via Re-parameterizing Diffusion Reverse Process AAAI 2024 Pruning Foundation Models for High Accuracy without Retraining EMNLP 2024 Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations ACL 2024 Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging EMNLP 2024 PTMQ: Post-training Multi-Bit Quantization of Neural Networks AAAI 2024 PTQ4DiT: Post-training Quantization for Diffusion Transformers NeurIPS 2024 PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression NeurIPS 2024