{"total":203,"rows":[{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2305.10924","title":"Structural Pruning for Diffusion Models","created":"2023-05-18","cited_by_count":195,"area":"diffusion"},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2308.10916","title":"Diffusion Model as Representation Learner","created":"2023-08-21","cited_by_count":95,"area":"diffusion"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"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":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69,"area":"mllm"},{"id":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67,"area":"diffusion"},{"id":"2404.11936","title":"LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights","created":"2024-04-18","cited_by_count":65,"area":"diffusion"},{"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":"2411.17787","title":"Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient","created":"2024-11-26","cited_by_count":33,"area":null},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32,"area":null},{"id":"2512.11130","title":"Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching","created":"2025-12-11","cited_by_count":28,"area":"distill"},{"id":"2310.03337","title":"Denoising Diffusion Step-aware Models","created":"2023-10-05","cited_by_count":24,"area":"diffusion"},{"id":"2312.01397","title":"Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22,"area":null},{"id":"2406.06911","title":"AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising","created":"2024-06-11","cited_by_count":22,"area":"diffusion"},{"id":"2407.04616","title":"Isomorphic Pruning for Vision Models","created":"2024-07-05","cited_by_count":21,"area":null},{"id":"2306.10460","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","created":"2023-06-18","cited_by_count":20,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2403.14729","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","created":"2024-03-21","cited_by_count":20,"area":null},{"id":"2310.02998","title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","created":"2023-10-04","cited_by_count":19,"area":"mllm"},{"id":"2510.06751","title":"OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot","created":"2025-10-08","cited_by_count":19,"area":"diffusion"},{"id":"2404.10445","title":"SparseDM: Toward Sparse Efficient Diffusion Models","created":"2024-04-16","cited_by_count":18,"area":"diffusion"},{"id":"2304.11595","title":"Segment Anything in Non-Euclidean Domains: Challenges and Opportunities","created":"2023-04-23","cited_by_count":16,"area":null},{"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":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2305.15798","title":"BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion","created":"2023-05-25","cited_by_count":13,"area":"diffusion"},{"id":"2410.07579","title":"Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2508.00697","title":"On-Device Diffusion Transformer Policy for Efficient Robot Manipulation","created":"2025-08-01","cited_by_count":13,"area":"diffusion"},{"id":"2407.04208","title":"AMD: Automatic Multi-step Distillation of Large-scale Vision Models","created":"2024-07-05","cited_by_count":12,"area":null},{"id":"2309.06626","title":"Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity","created":"2023-09-12","cited_by_count":10,"area":null},{"id":"2412.06289","title":"S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2510.14436","title":"MergeMoE: Efficient Compression of MoE Models via Expert Output Merging","created":"2025-10-16","cited_by_count":10,"area":"moe"},{"id":"2304.11818","title":"Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2312.05875","title":"Class-Aware Pruning for Efficient Neural Networks","created":"2023-12-10","cited_by_count":9,"area":null},{"id":"2406.11129","title":"Neural Lineage","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2403.15835","title":"Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2403.18955","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","created":"2024-03-03","cited_by_count":8,"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":"2411.18375","title":"Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models","created":"2024-11-27","cited_by_count":8,"area":"diffusion"},{"id":"2402.15978","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","created":"2024-02-25","cited_by_count":7,"area":null},{"id":"2412.00143","title":"Is Oracle Pruning the True Oracle?","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"2303.10597","title":"Partial Network Cloning","created":"2023-03-19","cited_by_count":6,"area":null},{"id":"2307.08695","title":"NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2312.09411","title":"OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2407.04803","title":"The Impact of Quantization and Pruning on Deep Reinforcement Learning Models","created":"2024-07-05","cited_by_count":6,"area":"deeprl"},{"id":"2410.00166","title":"EEG Emotion Copilot: Optimizing Lightweight LLMs for Emotional EEG Interpretation with Assisted Medical Record Generation","created":"2024-09-30","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":"2504.03454","title":"SpectR: Dynamically Composing LM Experts with Spectral Routing","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2508.00212","title":"Reinitializing weights vs units for maintaining plasticity in neural networks","created":"2025-07-31","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":"2602.00693","title":"Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2603.13792","title":"IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring","created":"2026-03-14","cited_by_count":6,"area":null},{"id":"2404.11630","title":"SNP: Structured Neuron-level Pruning to Preserve Attention Scores","created":"2024-04-18","cited_by_count":5,"area":null},{"id":"2406.07017","title":"MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations","created":"2024-06-11","cited_by_count":5,"area":null},{"id":"2503.16916","title":"Temporal Action Detection Model Compression by Progressive Block Drop","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2308.00093","title":"Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification","created":"2023-07-28","cited_by_count":4,"area":null},{"id":"2312.02470","title":"Generator Born from Classifier","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2312.08851","title":"Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2405.03715","title":"Iterative Filter Pruning for Concatenation-based CNN Architectures","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2406.19301","title":"MCNC: Manifold-Constrained Reparameterization for Neural Compression","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2408.11407","title":"Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection","created":"2024-08-21","cited_by_count":4,"area":"distill"},{"id":"2409.09085","title":"HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2410.11878","title":"Neural Metamorphosis","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2511.06016","title":"One-Shot Knowledge Transfer for Scalable Person Re-Identification","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2404.08016","title":"ONNXPruner: ONNX-Based General Model Pruning Adapter","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2502.17941","title":"Optimal Brain Apoptosis","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2504.13296","title":"Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2508.13836","title":"One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2601.17215","title":"JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers","created":"2026-01-23","cited_by_count":3,"area":null},{"id":"2603.24260","title":"Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep","created":"2026-03-25","cited_by_count":3,"area":"diffusion"},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"id":"2310.06344","title":"Filter Pruning For CNN With Enhanced Linear Representation Redundancy","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2311.02003","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2311.14517","title":"tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2403.06417","title":"Enhanced Sparsification via Stimulative Training","created":"2024-03-11","cited_by_count":2,"area":"distill"},{"id":"2405.01943","title":"Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2405.07194","title":"Differentiable Model Scaling using Differentiable Topk","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2405.11809","title":"Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2410.16151","title":"Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importance","created":"2024-10-21","cited_by_count":2,"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":"2411.10948","title":"Towards Accurate and Efficient Sub-8-Bit Integer Training","created":"2024-11-17","cited_by_count":2,"area":null},{"id":"2501.01118","title":"Pruning-based Data Selection and Network Fusion for Efficient Deep Learning","created":"2025-01-02","cited_by_count":2,"area":null},{"id":"2501.01601","title":"Few-shot Implicit Function Generation via Equivariance","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2501.16917","title":"B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2506.12041","title":"Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2508.11287","title":"CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2602.14302","title":"Floe: Federated Specialization for Real-Time LLM-SLM Inference","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2603.19873","title":"SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2304.07973","title":"Frequency Regularization: Restricting Information Redundancy of Convolutional Neural Networks","created":"2023-04-17","cited_by_count":1,"area":null}],"next_cursor":"100"}