{"total":16,"rows":[{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2308.02350","title":"RobustMQ: Benchmarking Robustness of Quantized Models","created":"2023-08-04","cited_by_count":19,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2304.03968","title":"Benchmarking the Robustness of Quantized Models","created":"2023-04-08","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":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2603.19296","title":"TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2306.08960","title":"Neural Network Compression using Binarization and Few Full-Precision Weights","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2312.13575","title":"ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2407.12075","title":"Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2507.02222","title":"High-Fidelity Differential-information Driven Binary Vision Transformer","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2602.03176","title":"BinaryDemoire: Moir\\'e-Aware Binarization for Image Demoir\\'eing","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2608.15602","title":"FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}