Model Compression

Pipeline Parallelism with Controllable Memory NeurIPS 2024 Plug-and-Play Diffusion Distillation CVPR 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 Privacy-Preserving Face Recognition Using Trainable Feature Subtraction CVPR 2024 Probabilistically Robust Watermarking of Neural Networks IJCAI 2024 Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion AAAI 2024 PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA ACL 2024 Promoting Data and Model Privacy in Federated Learning through Quantized LoRA EMNLP 2024 PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning EMNLP 2024 Provable Robustness against a Union of L_0 Adversarial Attacks AAAI 2024 ProxyFusion: Face Feature Aggregation Through Sparse Experts NeurIPS 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 Multilingual Large Language Models for Multilingual Inference EMNLP 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 QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning EMNLP 2024 QEFT: Quantization for Efficient Fine-Tuning of LLMs EMNLP 2024 QTIP: Quantization with Trellises and Incoherence Processing NeurIPS 2024 QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation NeurIPS 2024 Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models ACL 2024 QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models EMNLP 2024