{"total":22,"rows":[{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2311.12023","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","created":"2023-11-20","cited_by_count":92,"area":null},{"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":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24,"area":null},{"id":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2602.20208","title":"Model Merging in the Essential Subspace","created":"2026-02-23","cited_by_count":7,"area":null},{"id":"2602.02696","title":"NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2501.17905","title":"DReSS: Data-driven Regularized Structured Streamlining for Large Language Models","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2409.08771","title":"In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2505.13547","title":"Exploring Federated Pruning for Large Language Models","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2507.14481","title":"DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2410.01309","title":"Getting Free Bits Back from Rotational Symmetries in LLMs","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2501.15278","title":"PIP: Perturbation-based Iterative Pruning for Large Language Models","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2506.02077","title":"Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition","created":"2025-06-02","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":"2606.19164","title":"Data-Aware Model Merging in the Essential Subspace for Multi-Task Knowledge Aggregation","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2410.12513","title":"FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2505.08256","title":"Clustering-Based Low-Rank Matrix Approximation for Medical Image Compression","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2606.00312","title":"Stochastic Rounding Increases Small Singular Values","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.21039","title":"Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}