{"total":18,"rows":[{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86,"area":null},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2302.14705","title":"AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers","created":"2023-02-28","cited_by_count":24,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2410.14578","title":"Large Language Models Are Overparameterized Text Encoders","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2209.00625","title":"SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance","created":"2022-08-30","cited_by_count":4,"area":null},{"id":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","cited_by_count":3,"area":null},{"id":"2209.09130","title":"SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2205.09869","title":"Transformer with Memory Replay","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2507.07954","title":"Input Conditioned Layer Dropping in Speech Foundation Models","created":"2025-07-10","cited_by_count":2,"area":null},{"id":"2208.00483","title":"Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers","created":"2022-07-31","cited_by_count":1,"area":null},{"id":"2507.18448","title":"Restoring Rhythm: Punctuation Restoration Using Transformer Models for Bangla, A Low-Resource Language","created":"2025-07-24","cited_by_count":0,"area":null}],"next_cursor":null}