Kun Yang

AI-generated C++ code incurs 5-8% more compute costs and increased review efforts due to its distinct quality profile, but targeted feedback can substantially improve its performance.

PFAdapter cuts communication costs by nearly 50% while boosting accuracy in personalized federated learning for MLLMs.

LOLLA achieves up to 92% throughput gains over traditional link adaptation methods in 5G networks, revolutionizing performance in high-mobility scenarios.

Aggressive pursuit strategies can yield nearly 50% more thrust for quadcopters by relaxing traditional visibility constraints during interception.

MLLMs can be blind to the consequences of their actions, and simply scaling model size won't fix the problem.

Ditch VAEs and AMP: SLMP learns structured motion priors in a spherical latent space, enabling stable random sampling of diverse and valid humanoid behaviors without information loss.

By grounding reasoning within the topology of a global interaction graph, ManCAR achieves up to 46.88% relative improvement in NDCG@10 compared to state-of-the-art sequential recommendation baselines.