Ziliang Zhao

LLMs can now recall relevant information from long interaction histories without retraining, thanks to a state-adaptive memory framework that uses lightweight cues to reconstruct distant information on demand.

Today's best language models can barely make sense of your messy group chats and fragmented digital life, achieving only 19% accuracy on a new benchmark of real-world reasoning.

Achieve zero-collision embedding tables in production recommenders without sacrificing training speed, unlocking better personalization via fresher and higher-quality item embeddings.