{"total":21,"rows":[{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2206.03452","title":"Can CNNs Be More Robust Than Transformers?","created":"2022-06-07","cited_by_count":38,"area":null},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2409.19660","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","created":"2024-09-29","cited_by_count":14,"area":null},{"id":"2309.00655","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion","created":"2023-09-01","cited_by_count":11,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2210.00640","title":"Wide Attention Is The Way Forward For Transformers?","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2108.03645","title":"Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2207.03481","title":"Training Transformers Together","created":"2022-07-07","cited_by_count":5,"area":null},{"id":"2205.10505","title":"A Study on Transformer Configuration and Training Objective","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2302.00247","title":"TAPAS: Fast and Automatic Derivation of Tensor Parallel Strategies for Large Neural Networks","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2301.10750","title":"Out of Distribution Performance of State of Art Vision Model","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2306.00103","title":"ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2407.10157","title":"SACNet: A Spatially Adaptive Convolution Network for 2D Multi-organ Medical Segmentation","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2306.12100","title":"Efficient ResNets: Residual Network Design","created":"2023-06-21","cited_by_count":0,"area":null},{"id":"2310.12818","title":"Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2507.20180","title":"MoCTEFuse: Illumination-Gated Mixture of Chiral Transformer Experts for Multi-Level Infrared and Visible Image Fusion","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2512.19731","title":"Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems","created":"2025-12-17","cited_by_count":0,"area":null}],"next_cursor":null}