Tao Zou

CORE-MTL achieves superior generalization by separating task-relevant information from noise, outperforming traditional methods in multi-task learning benchmarks.

Forget everything you thought you knew about multimodal agent memory: TaskMem learns what to remember on the fly, boosting VQA accuracy by up to 7% without even looking at the raw video.

A new point cloud representation and attention mechanism unlocks state-of-the-art in-hospital mortality prediction from messy, incomplete real-world EHR data.