{"total":53,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43,"area":null},{"id":"2405.12250","title":"Your Transformer is Secretly Linear","created":"2024-05-19","cited_by_count":23,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2503.16843","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models","created":"2025-03-21","cited_by_count":11,"area":"mllm"},{"id":"2311.09550","title":"A Speed Odyssey for Deployable Quantization of LLMs","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2506.18931","title":"Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs","created":"2025-06-21","cited_by_count":10,"area":"alignment"},{"id":"2504.09897","title":"TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models","created":"2025-04-14","cited_by_count":9,"area":"mllm"},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2510.07985","title":"Fewer Weights, More Problems: A Practical Attack on LLM Pruning","created":"2025-10-09","cited_by_count":7,"area":null},{"id":"2412.03587","title":"Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models","created":"2024-11-26","cited_by_count":5,"area":null},{"id":"2502.13533","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.09657","title":"T\\'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2507.16872","title":"CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2510.21834","title":"Restoring Pruned Large Language Models via Lost Component Compensation","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2408.14470","title":"Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2601.06788","title":"Artificial Entanglement in the Fine-Tuning of Large Language Models","created":"2026-01-11","cited_by_count":2,"area":null},{"id":"2602.04019","title":"Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2503.07552","title":"Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2504.19538","title":"Towards Faster and More Compact Foundation Models for Molecular Property Prediction","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2506.12876","title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2511.19935","title":"EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.00942","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2603.13418","title":"GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.23730","title":"An Adapter-free Fine-tuning Approach for Tuning 3D Foundation Models","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2407.17029","title":"Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2408.11746","title":"Mixed Sparsity Training: Achieving 4$\\times$ FLOP Reduction for Transformer Pretraining","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2412.15127","title":"Adaptive Pruning for Large Language Models with Structural Importance Awareness","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2506.07695","title":"Towards a Small Language Model Lifecycle Framework","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.11042","title":"GenFT: A Generative Parameter-Efficient Fine-Tuning Method for Pretrained Foundation Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.11120","title":"SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models","created":"2025-06-10","cited_by_count":0,"area":"distill"},{"id":"2509.06836","title":"COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2601.22002","title":"Understanding Rate-Distortion Performance in Distributed Transformer Inference","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.27383","title":"Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.09008","title":"Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models","created":"2026-05-09","cited_by_count":0,"area":"lr"},{"id":"2605.12207","title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.22587","title":"TriSP: Tri-Signal Structured Pruning for Large Language Models","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.32615","title":"Stabilizing the Dynamic Low-Rank Training","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}