{"total":38,"rows":[{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2402.10517","title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","created":"2024-02-16","cited_by_count":54,"area":null},{"id":"2212.12294","title":"FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos","created":"2022-12-23","cited_by_count":46,"area":null},{"id":"2111.09136","title":"IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization","created":"2021-11-17","cited_by_count":43,"area":null},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2105.08952","title":"BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer","created":"2021-05-19","cited_by_count":20,"area":null},{"id":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"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":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2207.10188","title":"Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2211.14928","title":"Class-based Quantization for Neural Networks","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2510.10467","title":"AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2211.16726","title":"Boosted Dynamic Neural Networks","created":"2022-11-30","cited_by_count":8,"area":null},{"id":"2304.06724","title":"GradMDM: Adversarial Attack on Dynamic Networks","created":"2023-04-01","cited_by_count":8,"area":null},{"id":"2103.02904","title":"Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2105.02953","title":"Recognition of handwritten MNIST digits on low-memory 2 Kb RAM Arduino board using LogNNet reservoir neural network","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2301.00290","title":"BARVINN: Arbitrary Precision DNN Accelerator Controlled by a RISC-V CPU","created":"2022-12-31","cited_by_count":6,"area":null},{"id":"2305.08117","title":"MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2103.01435","title":"Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2210.15623","title":"Neural Networks with Quantization Constraints","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2312.02210","title":"Low-Precision Mixed-Computation Models for Inference on Edge","created":"2023-12-03","cited_by_count":4,"area":null},{"id":"2506.17870","title":"NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN","created":"2025-06-22","cited_by_count":4,"area":null},{"id":"2105.01353","title":"One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2506.11431","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2510.20673","title":"Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2502.07820","title":"Low-Rank Compression for IMC Arrays","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2607.23047","title":"MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models","created":"2026-07-25","cited_by_count":2,"area":null},{"id":"2206.12191","title":"Computational Complexity Evaluation of Neural Network Applications in Signal Processing","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2207.03088","title":"Attention Round for Post-Training Quantization","created":"2022-07-07","cited_by_count":1,"area":null},{"id":"2510.02822","title":"FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2110.00916","title":"Progressive Transmission and Inference of Deep Learning Models","created":"2021-10-03","cited_by_count":0,"area":null},{"id":"2303.11291","title":"Mobiprox: Supporting Dynamic Approximate Computing on Mobiles","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2407.11037","title":"ISQuant: apply squant to the real deployment","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2502.01199","title":"Nearly Lossless Adaptive Bit Switching","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2503.03228","title":"Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2508.15685","title":"Row-Column Hybrid Grouping for Fault-Resilient Multi-Bit Weight Representation on IMC Arrays","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2602.12609","title":"QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching","created":"2026-02-13","cited_by_count":0,"area":null}],"next_cursor":null}