{"total":7,"rows":[{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2304.10719","title":"FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2403.02037","title":"Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2510.27677","title":"Vision Transformer for Robust Occluded Person Reidentification in Complex Surveillance Scenes","created":"2025-10-31","cited_by_count":0,"area":null}],"next_cursor":null}