{"total":22,"rows":[{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159,"area":null},{"id":"2503.23844","title":"FlexiMo: A Flexible Remote Sensing Foundation Model","created":"2025-03-31","cited_by_count":24,"area":null},{"id":"2503.17970","title":"PathoHR: Breast Cancer Survival Prediction on High-Resolution Pathological Images","created":"2025-03-23","cited_by_count":9,"area":null},{"id":"2412.20601","title":"MATEY: multiscale adaptive foundation models for spatiotemporal physical systems","created":"2024-12-29","cited_by_count":5,"area":null},{"id":"2408.12396","title":"Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2504.01792","title":"UniViTAR: Unified Vision Transformer with Native Resolution","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2506.13277","title":"SeqPE: Transformer with Sequential Position Encoding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.06093","title":"Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2603.00543","title":"Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark","created":"2026-02-28","cited_by_count":2,"area":null},{"id":"2406.13860","title":"Liveness Detection in Computer Vision: Transformer-based Self-Supervised Learning for Face Anti-Spoofing","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2409.04082","title":"SDformerFlow: Spatiotemporal swin spikeformer for event-based optical flow estimation","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2602.24222","title":"MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2609.15018","title":"G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2504.03749","title":"Input Resolution Downsizing as a Compression Technique for Vision Deep Learning Systems","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2510.16209","title":"StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2604.23798","title":"ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.12168","title":"On What We Can Learn from Low-Resolution Data","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17472","title":"Weighted Reverse Convolution for Feature Upsampling","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.00580","title":"Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.02792","title":"PixelUp: Zero-Shot Semantic Feature Upsampling for Fine-Grained Vision Tasks","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.28706","title":"Variable-Granularity Tokenization for High-Resolution Object Detection","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.03216","title":"ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}