{"total":20,"rows":[{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"area":null},{"id":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2304.03986","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","created":"2023-04-08","cited_by_count":18,"area":null},{"id":"2205.13299","title":"Federated Split BERT for Heterogeneous Text Classification","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2302.09108","title":"ViTA: A Vision Transformer Inference Accelerator for Edge Applications","created":"2023-02-17","cited_by_count":11,"area":null},{"id":"2407.17879","title":"HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2401.11851","title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2405.19915","title":"P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2504.16269","title":"COBRA: Algorithm-Architecture Co-optimized Binary Transformer Accelerator for Edge Inference","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2411.18148","title":"A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2502.08807","title":"InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNs","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2110.10957","title":"Vis-TOP: Visual Transformer Overlay Processor","created":"2021-10-21","cited_by_count":2,"area":null},{"id":"2407.12070","title":"Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2110.07331","title":"Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2304.01483","title":"Blockwise Compression of Transformer-based Models without Retraining","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2303.09184","title":"Block-wise Bit-Compression of Transformer-based Models","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2510.10676","title":"Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translation","created":"2025-10-12","cited_by_count":0,"area":null}],"next_cursor":null}