 Argus: Vision-Centric Reasoning with Grounded Chain-of-ThoughtComputer Vision and Pattern Recognition (CVPR), 2025 |
 Vision-Language Modeling Meets Remote Sensing: Models, Datasets and PerspectivesIEEE Geoscience and Remote Sensing Magazine (GRSM), 2025 |
 MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane RepresentationInternational Conference on Learning Representations (ICLR), 2025 |
 RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and SafetyComputer Vision and Pattern Recognition (CVPR), 2025 |
 Scaling Vision Pre-Training to 4K ResolutionComputer Vision and Pattern Recognition (CVPR), 2025 |
 Seeing What Matters: Empowering CLIP with Patch Generation-to-SelectionComputer Vision and Pattern Recognition (CVPR), 2025 |
