{"total":13,"rows":[{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163,"area":null},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111,"area":null},{"id":"2404.14619","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","created":"2024-04-22","cited_by_count":75,"area":null},{"id":"2405.13226","title":"Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum","created":"2024-05-21","cited_by_count":26,"area":null},{"id":"2306.00238","title":"Bytes Are All You Need: Transformers Operating Directly On File Bytes","created":"2023-05-31","cited_by_count":18,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2212.10553","title":"RangeAugment: Efficient Online Augmentation with Range Learning","created":"2022-12-20","cited_by_count":8,"area":null},{"id":"2407.13170","title":"Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement","created":"2024-07-18","cited_by_count":3,"area":null},{"id":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2410.12584","title":"Self-DenseMobileNet: A Robust Framework for Lung Nodule Classification using Self-ONN and Stacking-based Meta-Classifier","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2309.04502","title":"On the Efficacy of Multi-scale Data Samplers for Vision Applications","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2510.03276","title":"QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2601.08190","title":"Human-inspired Global-to-Parallel Multi-scale Encoding for Lightweight Vision Models","created":"2026-01-13","cited_by_count":0,"area":null}],"next_cursor":null}