Model Compression

A Brain-Inspired Way of Reducing the Network Complexity via Concept-Regularized Coding for Emotion Recognition AAAI 2024 Accelerating Transformers with Spectrum-Preserving Token Merging NeurIPS 2024 A Comprehensive Evaluation of Quantization Strategies for Large Language Models ACL 2024 Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space ACL 2024 AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models EMNLP 2024 Adaptive Depth Networks with Skippable Sub-Paths NeurIPS 2024 Adversarial Distillation Based on Slack Matching and Attribution Region Alignment CVPR 2024 AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models ACL 2024 AFPQ: Asymmetric Floating Point Quantization for LLMs ACL 2024 A Lightweight U-like Network Utilizing Neural Memory Ordinary Differential Equations for Slimming the Decoder IJCAI 2024 All Rivers Run to the Sea: Private Learning with Asymmetric Flows CVPR 2024 AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality EMNLP 2024 AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models NeurIPS 2024 ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models NeurIPS 2024 AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking NeurIPS 2024 A Multi-Level Framework for Accelerating Training Transformer Models ICLR 2024 An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding NeurIPS 2024 ApiQ: Finetuning of 2-Bit Quantized Large Language Model EMNLP 2024 AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries AAAI 2024 A Study of Parameter Efficient Fine-tuning by Learning to Efficiently Fine-Tune EMNLP 2024 Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models CVPR 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts NeurIPS 2024 BASS: Batched Attention-optimized Speculative Sampling ACL 2024 BiDM: Pushing the Limit of Quantization for Diffusion Models NeurIPS 2024