Model Compression

Concealing Sensitive Samples against Gradient Leakage in Federated Learning AAAI 2024 Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation ICLR 2024 Data-Free Quantization via Pseudo-label Filtering CVPR 2024 DB-LLM: Accurate Dual-Binarization for Efficient LLMs ACL 2024 Debiased Distribution Compression ICML 2024 Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression ICML 2024 Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models NeurIPS 2024 Dense Vision Transformer Compression with Few Samples CVPR 2024 DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism NeurIPS 2024 Differentially Private Knowledge Distillation via Synthetic Text Generation ACL 2024 DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification NeurIPS 2024 DimA: A Parameter-efficient Fine-tuning Method with Knowledge Transfer Based on Transformer COLING 2024 DisCEdit: Model Editing by Identifying Discriminative Components NeurIPS 2024 Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models NeurIPS 2024 Disguise without Disruption: Utility-Preserving Face De-identification AAAI 2024 Ditto: Quantization-aware Secure Inference of Transformers upon MPC ICML 2024 Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization NAACL 2024 Divide-or-Conquer? Which Part Should You Distill Your LLM? EMNLP 2024 DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models EMNLP 2024 Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study COLING 2024 Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks NAACL 2024 Don't Look Twice: Faster Video Transformers with Run-Length Tokenization NeurIPS 2024 Do Topological Characteristics Help in Knowledge Distillation? ICML 2024 Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity EMNLP 2024 Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding ACL 2024