{"total":98,"rows":[{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88,"area":null},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2402.05147","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","created":"2024-02-07","cited_by_count":27,"area":null},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21,"area":null},{"id":"2408.03291","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","created":"2024-08-06","cited_by_count":19,"area":null},{"id":"2212.04780","title":"Genie: Show Me the Data for Quantization","created":"2022-12-09","cited_by_count":17,"area":null},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2410.05437","title":"ESPACE: Dimensionality Reduction of Activations for Model Compression","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2401.01543","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2206.10844","title":"Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices","created":"2022-06-22","cited_by_count":12,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2311.06798","title":"MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization","created":"2023-11-12","cited_by_count":7,"area":null},{"id":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","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":"2311.05109","title":"Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2405.05171","title":"Custom Gradient Estimators are Straight-Through Estimators in Disguise","created":"2024-05-08","cited_by_count":6,"area":null},{"id":"2208.09708","title":"DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2406.08001","title":"Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2503.02394","title":"BHViT: Binarized Hybrid Vision Transformer","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","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":"2307.04535","title":"QBitOpt: Fast and Accurate Bitwidth Reallocation during Training","created":"2023-07-10","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":"2410.10714","title":"SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2510.18784","title":"CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2406.02629","title":"SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2406.14082","title":"FLoCoRA: Federated learning compression with low-rank adaptation","created":"2024-06-20","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":"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":"2301.07266","title":"ACQ: Improving Generative Data-free Quantization Via Attention Correction","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2308.09511","title":"ResQ: Residual Quantization for Video Perception","created":"2023-08-18","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2402.06606","title":"RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2403.06497","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2404.19248","title":"Scheduling Weight Transitions for Quantization-Aware Training","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2407.05257","title":"OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks","created":"2024-07-07","cited_by_count":2,"area":null},{"id":"2409.13173","title":"Bilateral Sharpness-Aware Minimization for Flatter Minima","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2410.22110","title":"Data Generation for Hardware-Friendly Post-Training Quantization","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2412.05551","title":"GAQAT: gradient-adaptive quantization-aware training for domain generalization","created":"2024-12-07","cited_by_count":2,"area":null},{"id":"2503.11159","title":"Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2505.18113","title":"Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2507.17768","title":"Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2509.00859","title":"Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2509.07222","title":"Explaining How Quantization Disparately Skews a Model","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2510.14823","title":"FraQAT: Quantization Aware Training with Fractional bits","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2605.25966","title":"Mapping the Schedule x Bit-Width Boundary in Sub-100M Quantisation-Aware Training","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2403.08821","title":"Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2410.11203","title":"Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2501.09849","title":"Coded Deep Learning: Framework and Algorithm","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2502.00490","title":"Oscillations Make Neural Networks Robust to Quantization","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2502.14075","title":"Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.00259","title":"Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstruction","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2506.10463","title":"Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2509.05576","title":"Sensitivity-Aware Post-Training Quantization for Deep Neural Networks","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2509.14029","title":"Deep Learning-Driven Peptide Classification in Biological Nanopores","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2511.01462","title":"Efficiently Training A Flat Neural Network Before It has been Quantizated","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2609.27202","title":"Reliable Federated TinyML Deployment for IoT Security","created":"2026-09-23","cited_by_count":1,"area":null},{"id":"2305.15536","title":"RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2309.13773","title":"GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2310.10321","title":"Hamming Encoder: Mining Discriminative k-mers for Discrete Sequence Classification","created":"2023-10-16","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":"2503.08668","title":"SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2507.12196","title":"A Selective Quantization Tuner for ONNX Models","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.02457","title":"Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.03763","title":"Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2511.08360","title":"Extreme Model Compression with Structured Sparsity at Low Precision","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2511.17633","title":"BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.22660","title":"Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.19017","title":"Why ReLU? A Bit-Model Dichotomy for Deep Network Training","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.05964","title":"QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.09220","title":"TinyNeRV: Compact Neural Video Representations via Capacity Scaling, Distillation, and Low-Precision Inference","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.20295","title":"Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.25087","title":"Neural Network Quantization by Learning Low-Loss Subspaces","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.03919","title":"Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.24173","title":"SandwichQuant: Which Parameters Matter Before and After Quantization?","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.32659","title":"Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32902","title":"Linger and Lose: Knowledge Collapse in Low-Bit Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00738","title":"Q-MINO: A Minimal-Norm Method for Quantization-Aware Training","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03218","title":"VisionMX: Unlocking Microscaling Post-Training Quantization for Vision Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.07853","title":"Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.17637","title":"Mixed Precision Scaling Laws for Quantized Pretraining","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}