Wenqi Huang

Coding agents can now be evaluated on tasks that truly test their problem-solving skills, rather than their ability to recall previously seen solutions.

Jointly estimating the B0 field and distortion-free images directly from k-space data leads to unprecedented improvements in MRI accuracy and detail fidelity, especially in challenging high b-value scenarios.

Ditch the patches: Implicit Neural Representations can now segment highly variable pathological lesions in whole-slide images, even outperforming standard methods at lower resolutions.

Off-policy reinforcement learning can boost LLM reasoning by 12.5% and solve 40% more problems compared to on-policy methods, simply by re-evaluating and reusing historically difficult samples.