Han Zhu

TransRetrieval achieves a 2.53% revenue boost while slashing computational costs by 85%, revolutionizing recommendation retrieval in industrial settings.

Mining high-quality samples from CTR data can dramatically enhance multimodal representation learning, leading to superior prediction accuracy.

Evidence-focused reasoning in RecGPT-Mobile-V2 boosts query quality by over 5% while slashing hard-failure rates to a mere 1.6%.

RecVerse outperforms traditional simulators by maintaining a nuanced understanding of user intent and memory, leading to more realistic shopping behaviors.

MetaStrategy achieves a remarkable 27.93% win rate in generative ranking calls while enhancing user engagement metrics significantly, all without increasing response time.

Re-ranking control alone boosts key performance metrics by over 2%, but extending it to fine ranking unlocks even greater gains without sacrificing system stability.

LoopMemGR transforms generative recommendation by integrating past recommendations into the memory framework, leading to more informed and effective predictions.

Future interactions can be harnessed to significantly boost recommendation accuracy without compromising inference efficiency.

Context-aware routing and compression in SPARC leads to superior generative recommendations by preserving crucial information without inflating input size.

By cutting end-to-end serving resource consumption by over 50% while boosting user engagement metrics, RecGPT-V3 redefines efficiency in large-scale recommender systems.