{"total":193,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"area":null},{"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":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"area":null},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55,"area":null},{"id":"2202.07471","title":"SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation","created":"2022-02-14","cited_by_count":55,"area":null},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54,"area":null},{"id":"2305.18403","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","created":"2023-05-28","cited_by_count":53,"area":null},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"area":null},{"id":"2404.00781","title":"Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning","created":"2024-03-31","cited_by_count":50,"area":null},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"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":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2104.11408","title":"Neural Mean Discrepancy for Efficient Out-of-Distribution Detection","created":"2021-04-23","cited_by_count":42,"area":null},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2304.01230","title":"SEENN: Towards Temporal Spiking Early-Exit Neural Networks","created":"2023-04-02","cited_by_count":41,"area":null},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2302.14623","title":"Fast as CHITA: Neural Network Pruning with Combinatorial Optimization","created":"2023-02-28","cited_by_count":40,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2310.18356","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2108.08910","title":"Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search","created":"2021-08-18","cited_by_count":34,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30,"area":null},{"id":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","cited_by_count":29,"area":null},{"id":"2410.11112","title":"Differentiable Weightless Neural Networks","created":"2024-10-14","cited_by_count":28,"area":null},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27,"area":null},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26,"area":null},{"id":"2410.14720","title":"SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models","created":"2024-10-14","cited_by_count":25,"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":"2312.01397","title":"Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2212.06140","title":"Fairify: Fairness Verification of Neural Networks","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2102.07156","title":"ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2204.02738","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2210.09223","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","created":"2022-10-14","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":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2206.00843","title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2406.07831","title":"ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2111.00162","title":"You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership","created":"2021-10-30","cited_by_count":18,"area":null},{"id":"2403.12983","title":"OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization","created":"2024-03-02","cited_by_count":18,"area":null},{"id":"2105.14713","title":"1xN Pattern for Pruning Convolutional Neural Networks","created":"2021-05-31","cited_by_count":16,"area":null},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16,"area":null},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2308.10438","title":"Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks","created":"2023-08-21","cited_by_count":15,"area":null},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2310.02277","title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","created":"2023-09-29","cited_by_count":13,"area":null},{"id":"2210.04311","title":"Pruning Adversarially Robust Neural Networks without Adversarial Examples","created":"2022-10-09","cited_by_count":12,"area":null},{"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":"2403.07094","title":"FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2411.18376","title":"Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2109.10795","title":"Neural network relief: a pruning algorithm based on neural activity","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2202.07861","title":"Practical Network Acceleration with Tiny Sets","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2308.02060","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","created":"2023-08-03","cited_by_count":10,"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":"2411.01800","title":"Expanding Sparse Tuning for Low Memory Usage","created":"2024-11-04","cited_by_count":10,"area":null},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2403.18708","title":"Dense Vision Transformer Compression with Few Samples","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2504.19274","title":"TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks","created":"2025-04-27","cited_by_count":9,"area":null},{"id":"2107.06304","title":"Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks","created":"2021-07-13","cited_by_count":8,"area":null},{"id":"2210.11639","title":"HesScale: Scalable Computation of Hessian Diagonals","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2302.14670","title":"Balanced Training for Sparse GANs","created":"2023-02-28","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":"2408.17163","title":"The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information","created":"2024-08-30","cited_by_count":8,"area":null},{"id":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2107.02550","title":"Universal approximation and model compression for radial neural networks","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2205.10121","title":"Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2408.16772","title":"An Effective Information Theoretic Framework for Channel Pruning","created":"2024-08-14","cited_by_count":7,"area":null},{"id":"2106.07769","title":"The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2208.08562","title":"Restructurable Activation Networks","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2309.11531","title":"EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2408.15126","title":"Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2510.18030","title":"From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2101.02338","title":"Max-Affine Spline Insights Into Deep Network Pruning","created":"2021-01-07","cited_by_count":5,"area":null},{"id":"2302.03281","title":"Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning","created":"2023-02-07","cited_by_count":5,"area":null}],"next_cursor":"100"}