Yixin Zhu

LLM-based narrative evaluation reveals that the *way* people tell their stories is a stronger predictor of mental health than the specific words they use.

By progressively expanding boundary predictions, PBE-UNet effectively focuses on challenging segmentation error regions in ultrasound images, leading to state-of-the-art performance.

Forget painstakingly teleoperating robots or waiting for CPU planners: AutoMoMa unlocks 80x faster generation of kinematically valid mobile manipulation trajectories, finally making large-scale data practical.

Visual inputs can hijack the moral compass of VLMs, causing them to abandon carefully tuned text-based safety protocols and make surprisingly unethical decisions.

A new humanoid teleoperation system, OmniClone, achieves state-of-the-art control fidelity and generalization while drastically reducing computational cost, thanks to a diagnostic benchmark that exposes failure modes overlooked by aggregate metrics.