{"total":111,"rows":[{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243,"area":null},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82,"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":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"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":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2506.17639","title":"RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models","created":"2025-06-21","cited_by_count":23,"area":"vla"},{"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":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2505.22689","title":"SlimLLM: Accurate Structured Pruning for Large Language Models","created":"2025-05-28","cited_by_count":18,"area":null},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14,"area":"inference"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2502.15618","title":"Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing","created":"2025-02-21","cited_by_count":14,"area":null},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"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":"2507.00390","title":"MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE","created":"2025-07-01","cited_by_count":13,"area":"moe"},{"id":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2506.04179","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","created":"2025-06-04","cited_by_count":11,"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":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2407.19126","title":"Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"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":"2502.10216","title":"Forget the Data and Fine-Tuning! Just Fold the Network to Compress","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","cited_by_count":7,"area":null},{"id":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2502.03460","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2505.23807","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","created":"2025-05-27","cited_by_count":6,"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":"2509.14230","title":"NIRVANA: Structured Pruning Reimagined for Large Language Model Compression","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2512.02185","title":"Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2502.01705","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","created":"2025-02-03","cited_by_count":5,"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":"2507.07580","title":"COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2407.13331","title":"Reconstruct the Pruned Model without Any Retraining","created":"2024-07-18","cited_by_count":4,"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":"2409.00592","title":"Hyper-Compression: Model Compression via Hyperfunction","created":"2024-09-01","cited_by_count":3,"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":"2502.04348","title":"Prompt-based Depth Pruning of Large Language Models","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2505.17138","title":"RAP: Runtime Adaptive Pruning for LLM Inference","created":"2025-05-22","cited_by_count":3,"area":"inference"},{"id":"2505.20155","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2510.19389","title":"ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression","created":"2025-10-22","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":"2602.07804","title":"Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models","created":"2026-02-08","cited_by_count":3,"area":null},{"id":"2410.19185","title":"Tailored-LLaMA: Optimizing Few-Shot Learning in Pruned LLaMA Models with Task-Specific Prompts","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2503.18646","title":"ZeroLM: Data-Free Transformer Architecture Search for Language Models","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2505.00624","title":"FineScope : SAE-guided Data Selection Enables Domain Specific LLM Pruning and Finetuning","created":"2025-05-01","cited_by_count":2,"area":"mechinterp"},{"id":"2510.07782","title":"RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Models","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2601.07212","title":"MI-PRUN: Optimize Large Language Model Pruning via Mutual Information","created":"2026-01-12","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":"2603.16284","title":"Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation","created":"2026-03-17","cited_by_count":2,"area":"mllm"},{"id":"2605.15491","title":"Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.27786","title":"Locality-Aware Redundancy Pruning for LLM Depth Compression","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2605.31256","title":"Before Parc Ferm\\'e: RL-Time Pruning for Efficient Embodied LLMs in Autonomous Driving","created":"2026-05-29","cited_by_count":2,"area":"lr"},{"id":"2606.01850","title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.31382","title":"Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"id":"2405.15877","title":"Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2406.00030","title":"Large Language Model Pruning","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.03373","title":"SPAP: Structured Pruning via Alternating Optimization and Penalty Methods","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.03828","title":"IMPACT: Importance-Aware Activation Space Reconstruction","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2510.07227","title":"Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.14444","title":"A Free Lunch in LLM Compression: Revisiting Retraining after Pruning","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2510.22489","title":"Frustratingly Easy Task-aware Pruning for Large Language Models","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2510.24037","title":"Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.00780","title":"Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models","created":"2026-01-31","cited_by_count":1,"area":"vla"},{"id":"2602.02891","title":"TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.23795","title":"GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.08083","title":"High-Fidelity Pruning for Large Language Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.12272","title":"ActTail: Global Activation Sparsity in Large Language Models","created":"2026-02-18","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":"2604.23475","title":"Supernodes and Halos: Loss-Critical Hubs in LLM Feed-Forward Layers","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.26861","title":"Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT","created":"2026-06-25","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":"2504.03118","title":"NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2504.09803","title":"CUT: Pruning Pre-Trained Multi-Task Models into Compact Models for Edge Devices","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2505.24241","title":"Advantageous Parameter Expansion Training Makes Better Large Language Models","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2505.24469","title":"Smooth Model Compression without Fine-Tuning","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.12826","title":"LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling","created":"2025-06-15","cited_by_count":0,"area":"mllm"},{"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":"2507.14171","title":"IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning","created":"2025-07-10","cited_by_count":0,"area":null},{"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":"2510.02675","title":"HALO: Memory-Centric Heterogeneous Accelerator with 2.5D Integration for Low-Batch LLM Inference","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2511.18977","title":"FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2511.19495","title":"A Systematic Study of Compression Ordering for Large Language Models","created":"2025-11-23","cited_by_count":0,"area":"distill"},{"id":"2512.07090","title":"Leveraging KV Similarity for Online Structured Pruning in LLMs","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.22692","title":"FNF: Functional Network Fingerprint for Large Language Models","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.06822","title":"POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2605.01627","title":"Importance-Guided Basis Selection for Low-Rank Decomposition of Large Language Models","created":"2026-05-02","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":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":"100"}