Model Compression

High-Fidelity Gradient Inversion in Distributed Learning AAAI 2024 How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective NeurIPS 2024 How to Train the Teacher Model for Effective Knowledge Distillation ECCV 2024 HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning NeurIPS 2024 Identifiability of Product of Experts Models AISTATS 2024 IDGuard: Robust General Identity-centric POI Proactive Defense Against Face Editing Abuse CVPR 2024 Improving LoRA in Privacy-preserving Federated Learning ICLR 2024 In-Context Former: Lightning-fast Compressing Context for Large Language Model EMNLP 2024 Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning ICLR 2024 In defense of parameter sharing for model-compression ICLR 2024 In Defense of Structural Sparse Adapters for Concurrent LLM Serving EMNLP 2024 Instance-Level Dynamic LoRAs Composition for Cross-Task Generalization EMNLP 2024 Instructional Fingerprinting of Large Language Models NAACL 2024 IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact ACL 2024 Investigating Acceleration of LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with ‘LITE’ NAACL 2024 IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning AAAI 2024 Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning EMNLP 2024 Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting NeurIPS 2024 Keep it Private: Unsupervised Privatization of Online Text NAACL 2024 KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning ACL 2024 Knowledge boosting during low-latency inference Interspeech 2024 Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget NAACL 2024 Knowledge Editing for Large Language Models COLING 2024 KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches EMNLP 2024 KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization NeurIPS 2024