Xi Chen

The Temporal Ratio reveals how attention shifts between future and present frames can predict a model's ability to generalize compositional tasks in video-action contexts.

Transforming continuous geometric signals into structured discrete tokens leads to state-of-the-art performance in multi-animal tracking, even in the most challenging scenarios.

False positives in prostate MRI can closely mimic true cancers, complicating diagnosis and treatment decisions.

SkelEM achieves high-fidelity detail restoration in volume microscopy in under five steps, outperforming existing self-supervised methods.

The ABC framework empowers researchers with the largest open-source teleoperation dataset and a complete toolkit to accelerate advancements in behavior cloning for robotic manipulation.

Reusing cached plans can cut computational costs by over 80% without sacrificing performance, but only if you adaptively manage prediction mismatches.

SkillWiki revolutionizes agent skill management by linking skills to their evidence, enabling continuous evolution and governance in a way that current systems like Wikipedia and GitHub do not.

LabVLA achieves unprecedented success rates in executing complex laboratory protocols, outperforming all existing models in both familiar and novel settings.

2FFS slashes the sample complexity of best-action identification in stochastic minimax trees, proving that efficiency and accuracy can coexist in AI planning.