{"total":18,"rows":[{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"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":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20,"area":null},{"id":"2410.09615","title":"SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression","created":"2024-10-12","cited_by_count":12,"area":null},{"id":"2503.16672","title":"Accelerating Transformer Inference and Training with 2:4 Activation Sparsity","created":"2025-03-20","cited_by_count":9,"area":null},{"id":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2410.21271","title":"EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation","created":"2024-10-28","cited_by_count":7,"area":null},{"id":"2502.00899","title":"HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs","created":"2025-02-02","cited_by_count":3,"area":null},{"id":"2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2603.01376","title":"3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2512.13886","title":"OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2508.02128","title":"Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2606.28932","title":"DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2605.17289","title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.20214","title":"ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2610.16147","title":"BARTER: Compact Dynamic Sparse Training with Standard Dense Kernels","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18516","title":"Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions Too","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}