Feng Wu

PriorPose is proposed, a reference-guided correspondence framework that keeps the category prior explicit and solves canonicalization and alignment jointly in a shared feature space and sets new state-of-the-art results on most evaluated metrics, especially under strict pose thresholds.

IMA achieves high-fidelity text-to-image generation by adapting the model in real-time, preserving subject identity without pre-training on reference images.

Real-world coding tasks, reverse-engineered from actual commits and scenarios, make Tencent WorkBuddy Bench a game-changer in contamination-resistant evaluation for coding agents.

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.