{"total":59,"rows":[{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55,"area":null},{"id":"2302.12721","title":"LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version","created":"2023-02-24","cited_by_count":50,"area":null},{"id":"2106.03795","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","created":"2021-06-07","cited_by_count":44,"area":null},{"id":"2109.01163","title":"Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition","created":"2021-08-31","cited_by_count":42,"area":null},{"id":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33,"area":null},{"id":"2505.18809","title":"VORTA: Efficient Video Diffusion via Routing Sparse Attention","created":"2025-05-24","cited_by_count":23,"area":"diffusion"},{"id":"2204.01268","title":"Improving Monocular Visual Odometry Using Learned Depth","created":"2022-04-04","cited_by_count":17,"area":null},{"id":"2203.11629","title":"On Neural Network Equivalence Checking using SMT Solvers","created":"2022-03-22","cited_by_count":10,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2311.17350","title":"Implicit-explicit Integrated Representations for Multi-view Video Compression","created":"2023-11-29","cited_by_count":8,"area":null},{"id":"2505.09395","title":"Quantum-Enhanced Parameter-Efficient Learning for Typhoon Trajectory Forecasting","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2306.08125","title":"Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2403.04759","title":"Lifelong Intelligence Beyond the Edge using Hyperdimensional Computing","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2410.02237","title":"Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2201.11103","title":"Auto-Compressing Subset Pruning for Semantic Image Segmentation","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2211.17180","title":"Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2304.11251","title":"Machine Learning and the Future of Bayesian Computation","created":"2023-04-21","cited_by_count":4,"area":null},{"id":"2407.13331","title":"Reconstruct the Pruned Model without Any Retraining","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2305.07135","title":"Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2308.07641","title":"Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2502.02766","title":"Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2505.08474","title":"Distributed Quantum Neural Networks on Distributed Photonic Quantum Computing","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2507.21726","title":"Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2302.10483","title":"Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2305.17559","title":"Pruning at Initialization -- A Sketching Perspective","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2307.05972","title":"Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2503.01353","title":"Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2507.17725","title":"On the Interaction of Compressibility and Adversarial Robustness","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2508.05463","title":"Task complexity shapes internal representations and robustness in neural networks","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2101.08310","title":"Non-Convex Compressed Sensing with Training Data","created":"2021-01-20","cited_by_count":1,"area":null},{"id":"2111.05478","title":"SGD Through the Lens of Kolmogorov Complexity","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2312.03038","title":"Sample-based Dynamic Hierarchical Transformer with Layer and Head Flexibility via Contextual Bandit","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2403.17447","title":"Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2404.07532","title":"Bayesian Federated Model Compression for Communication and Computation Efficiency","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2407.17524","title":"StreamTinyNet: video streaming analysis with spatial-temporal TinyML","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2502.06095","title":"Rateless Joint Source-Channel Coding, and a Blueprint for 6G Semantic Communications System Design","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2506.21146","title":"Linearity-based neural network compression","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2603.06606","title":"LegoNet: Memory Footprint Reduction Through Block Weight Clustering","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2107.10998","title":"Pruning Ternary Quantization","created":"2021-07-23","cited_by_count":0,"area":null},{"id":"2212.05603","title":"Error-aware Quantization through Noise Tempering","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2305.08075","title":"Analyzing Compression Techniques for Computer Vision","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2305.10616","title":"Evaluation Metrics for DNNs Compression","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2309.10975","title":"SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2311.18102","title":"PatchBMI-Net: Lightweight Facial Patch-based Ensemble for BMI Prediction","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2312.07759","title":"IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2401.01801","title":"A quatum inspired neural network for geometric modeling","created":"2024-01-03","cited_by_count":0,"area":null},{"id":"2408.00923","title":"Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2409.08943","title":"Pushing Joint Image Denoising and Classification to the Edge","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2410.08979","title":"Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control","created":"2024-10-11","cited_by_count":0,"area":"deeprl"},{"id":"2412.15127","title":"Adaptive Pruning for Large Language Models with Structural Importance Awareness","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2505.24269","title":"INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2510.22058","title":"Pruning and Quantization Impact on Graph Neural Networks","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2510.22909","title":"Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2602.13244","title":"Responsible AI in Business","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2607.13043","title":"Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2609.04881","title":"From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}