Feng Wu

Real-world coding tasks can be evaluated without risk of contamination, thanks to a unique reverse-engineering approach that ensures task prompts are untraceable.

NegROI achieves superior 3D segmentation with fewer clicks by intelligently refining only the most ambiguous regions while effectively managing background confusion.

SL-S4Wave achieves state-of-the-art performance in arrhythmia detection while requiring significantly fewer labeled examples than traditional methods.

CapRL++ redefines caption quality through utility, enabling models to produce high-fidelity descriptions without the constraints of traditional supervised fine-tuning.

User corrections of AI agents are a goldmine: Echo shows how to automatically transform these noisy interactions into a 10% absolute improvement in code completion acceptance rates.

Decomposing GUI agent trajectories into verifiable milestones and auditing the evidence chain yields a 10% boost in RL training performance, outperforming single-judge reward systems.