{"total":142,"rows":[{"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":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256,"area":null},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2307.09782","title":"ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats","created":"2023-07-19","cited_by_count":44,"area":null},{"id":"2111.00465","title":"DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning","created":"2021-10-31","cited_by_count":41,"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":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","cited_by_count":39,"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":"2304.10136","title":"Diversifying the High-level Features for better Adversarial Transferability","created":"2023-04-20","cited_by_count":34,"area":null},{"id":"2110.15456","title":"FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding","created":"2021-10-28","cited_by_count":31,"area":null},{"id":"2206.11357","title":"GACT: Activation Compressed Training for Generic Network Architectures","created":"2022-06-22","cited_by_count":31,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28,"area":null},{"id":"2410.11112","title":"Differentiable Weightless Neural Networks","created":"2024-10-14","cited_by_count":28,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25,"area":null},{"id":"2110.14807","title":"L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization","created":"2021-10-27","cited_by_count":21,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2101.09868","title":"CPT: Efficient Deep Neural Network Training via Cyclic Precision","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2111.08988","title":"LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks","created":"2021-11-17","cited_by_count":19,"area":null},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2105.06002","title":"Lightweight compression of neural network feature tensors for collaborative intelligence","created":"2021-05-12","cited_by_count":17,"area":null},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17,"area":null},{"id":"2205.12268","title":"Wavelet Feature Maps Compression for Image-to-Image CNNs","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2111.02249","title":"Learned Image Compression for Machine Perception","created":"2021-11-03","cited_by_count":14,"area":null},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2301.00330","title":"Efficient On-device Training via Gradient Filtering","created":"2023-01-01","cited_by_count":13,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"id":"2206.09909","title":"Low-Precision Stochastic Gradient Langevin Dynamics","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2207.08822","title":"Is Integer Arithmetic Enough for Deep Learning Training?","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2502.12346","title":"QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models","created":"2025-02-17","cited_by_count":11,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2202.07861","title":"Practical Network Acceleration with Tiny Sets","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2203.06673","title":"FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support","created":"2022-03-13","cited_by_count":10,"area":null},{"id":"2309.15275","title":"Efficient Low-rank Backpropagation for Vision Transformer Adaptation","created":"2023-09-26","cited_by_count":10,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2203.10991","title":"Minimum Variance Unbiased N:M Sparsity for the Neural Gradients","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2301.09522","title":"Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff","created":"2023-01-23","cited_by_count":8,"area":null},{"id":"2105.04246","title":"In-Hindsight Quantization Range Estimation for Quantized Training","created":"2021-05-10","cited_by_count":7,"area":null},{"id":"2105.07102","title":"Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence","created":"2021-05-15","cited_by_count":7,"area":null},{"id":"2106.13914","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","created":"2021-06-26","cited_by_count":7,"area":null},{"id":"2211.02412","title":"Emergent Quantized Communication","created":"2022-11-04","cited_by_count":7,"area":null},{"id":"2410.15252","title":"Lossless KV Cache Compression to 2%","created":"2024-10-20","cited_by_count":7,"area":"inference"},{"id":"2503.16134","title":"Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing","created":"2025-03-20","cited_by_count":7,"area":"ssm"},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2303.02095","title":"Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective","created":"2023-03-03","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":"2104.07329","title":"All-You-Can-Fit 8-Bit Flexible Floating-Point Format for Accurate and Memory-Efficient Inference of Deep Neural Networks","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2210.13361","title":"NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2305.18513","title":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","created":"2023-05-29","cited_by_count":5,"area":null},{"id":"2308.14949","title":"Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation","created":"2023-08-29","cited_by_count":5,"area":null},{"id":"2310.19991","title":"PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2406.16282","title":"Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2201.02863","title":"PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++","created":"2022-01-08","cited_by_count":4,"area":null},{"id":"2205.03960","title":"Neural Architecture Search using Property Guided Synthesis","created":"2022-05-08","cited_by_count":4,"area":null},{"id":"2307.04535","title":"QBitOpt: Fast and Accurate Bitwidth Reallocation during Training","created":"2023-07-10","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":"2312.05725","title":"FP8-BERT: Post-Training Quantization for Transformer","created":"2023-12-10","cited_by_count":4,"area":null},{"id":"2401.09916","title":"Enabling On-device Continual Learning with Binary Neural Networks","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2401.14110","title":"Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2110.03553","title":"Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving","created":"2021-10-07","cited_by_count":3,"area":null},{"id":"2212.02634","title":"QFT: Post-training quantization via fast joint finetuning of all degrees of freedom","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2305.03148","title":"CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2308.15308","title":"On-Device Learning with Binary Neural Networks","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2401.17269","title":"Effect of Weight Quantization on Learning Models by Typical Case Analysis","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2408.14267","title":"1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2502.06567","title":"Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study","created":"2025-02-10","cited_by_count":3,"area":"safety"},{"id":"2104.10853","title":"InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks","created":"2021-04-22","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2111.09389","title":"Low Precision Decentralized Distributed Training over IID and non-IID Data","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2203.07713","title":"LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference","created":"2022-03-15","cited_by_count":2,"area":null},{"id":"2207.06920","title":"Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2211.03741","title":"AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2211.08544","title":"Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2301.13464","title":"Training with Mixed-Precision Floating-Point Assignments","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2303.00972","title":"Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm","created":"2023-03-02","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":"2311.17323","title":"Mirage: An RNS-Based Photonic Accelerator for DNN Training","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2406.08830","title":"Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2406.16299","title":"Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other","created":"2024-06-24","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":"2501.10547","title":"HyperCam: Low-Power Onboard Computer Vision for IoT Cameras","created":"2025-01-17","cited_by_count":2,"area":null},{"id":"2502.04711","title":"Dynamic Frequency-Adaptive Knowledge Distillation for Speech Enhancement","created":"2025-02-07","cited_by_count":2,"area":"distill"},{"id":"2511.05187","title":"Gradient Prediction with Control Variates in the Cheap-Forward Regime","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2103.14493","title":"RCT: Resource Constrained Training for Edge AI","created":"2021-03-26","cited_by_count":1,"area":null}],"next_cursor":"100"}