FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation
Paper • 2609.16591 • Published • 16
None defined yet.
FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data