Jun Yang

MIRA not only boosts diagnostic accuracy but also transforms how medical visual agents evaluate the necessity and reliability of their tool use, achieving a remarkable reduction in harmful judgments.

MEGRAG achieves superior multi-hop reasoning by leveraging a multi-granular evidence graph, leading to more accurate answers with reduced noise and redundancy.

HarnessCompass boosts agent performance by 22% in just five iterations, setting a new standard for generalization in automatic harness evolution.

UniSGR achieves a breakthrough in recommendation systems by seamlessly integrating semantic ID generation with multi-objective ranking, leading to superior performance in e-commerce applications.

Rolling-shutter distortions can be harnessed to achieve accurate velocity estimates of fast-moving spheres, even in the absence of texture.

ProMSA achieves superior accuracy in KB-VQA by dynamically selecting retrieval strategies, outperforming traditional fixed pipelines.

Mistakes in human demonstrations can enhance robot learning when properly harnessed, revealing a new dimension of value estimation that traditional methods overlook.

ReMMD-Agent achieves a remarkable 41.80% accuracy in detecting misinformation across complex multilingual and multi-image scenarios while slashing verification costs by up to 80%.

Achieving state-of-the-art multilingual reranking without costly relevance annotations, Querit-Reranker redefines efficiency in model adaptation.