{"total":32,"rows":[{"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":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2410.11988","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","created":"2024-10-15","cited_by_count":24,"area":null},{"id":"2407.16286","title":"A deeper look at depth pruning of LLMs","created":"2024-07-23","cited_by_count":23,"area":null},{"id":"2505.02819","title":"ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2501.17771","title":"2SSP: A Two-Stage Framework for Structured Pruning of LLMs","created":"2025-01-29","cited_by_count":12,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2501.19183","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2506.08436","title":"Olica: Efficient Structured Pruning of Large Language Models without Retraining","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2504.21174","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","created":"2025-04-29","cited_by_count":5,"area":null},{"id":"2507.17013","title":"laplax -- Laplace Approximations with JAX","created":"2025-07-22","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":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2604.00821","title":"Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2406.00061","title":"STAT: Shrinking Transformers After Training","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2602.08858","title":"FlattenGPT: Depth Compression for Transformer with Layer Flattening","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2608.08506","title":"Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2606.23568","title":"SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2405.05957","title":"OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning","created":"2024-05-09","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":"2602.06127","title":"Compressing LLMs with MoP: Mixture of Pruners","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2607.18284","title":"Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.12953","title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.29765","title":"PruneShift: A Framework for Evaluating Decision Reliability in Structured Pruning","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.02083","title":"XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.35579","title":"Output-aware Residual Stream Pruning for Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40127","title":"Learning Functional Subspaces for Neural Network Compression","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00432","title":"XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.18098","title":"From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits","created":"2026-10-13","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}