{"total":26,"rows":[{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2310.15638","title":"CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation","created":"2023-10-24","cited_by_count":94,"area":null},{"id":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49,"area":null},{"id":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26,"area":null},{"id":"2203.15952","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23,"area":null},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2206.12372","title":"QReg: On Regularization Effects of Quantization","created":"2022-06-24","cited_by_count":11,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2205.03494","title":"Online Model Compression for Federated Learning with Large Models","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2308.03290","title":"FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search","created":"2023-08-07","cited_by_count":6,"area":null},{"id":"2503.06921","title":"Task Vector Quantization for Memory-Efficient Model Merging","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2404.00103","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2409.09245","title":"Robust Training of Neural Networks at Arbitrary Precision and Sparsity","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2203.02833","title":"Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference","created":"2022-03-05","cited_by_count":2,"area":null},{"id":"2401.17544","title":"Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2508.03002","title":"Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.03472","title":"DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2111.10320","title":"Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression","created":"2021-11-19","cited_by_count":0,"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":"2407.14831","title":"Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns","created":"2024-07-20","cited_by_count":0,"area":null},{"id":"2607.26515","title":"HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}