{"total":19,"rows":[{"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":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"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":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"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":"2403.10799","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","created":"2024-03-16","cited_by_count":13,"area":null},{"id":"2404.09695","title":"LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models","created":"2024-04-15","cited_by_count":12,"area":null},{"id":"2405.10616","title":"Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization","created":"2024-05-17","cited_by_count":10,"area":null},{"id":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2602.00398","title":"MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2501.19090","title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2512.13494","title":"SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2507.03294","title":"MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2508.16680","title":"CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2510.01718","title":"Accelerating Attention with Basis Decomposition","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2604.21952","title":"Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.06216","title":"TIDE: Every Layer Knows the Token Beneath the Context","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}