object localization
- Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360° Firefighting Video
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection
- MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
- OmniTry: Virtual Try-On Anything without Masks
- SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation