Yu Liu

Fine-tuning LLMs in federated settings just got easier: SplitFT lets clients adapt their cut layers and LoRA ranks, boosting performance and slashing communication costs.

Bridging the gap between generative retrieval and ranking, RecoChain achieves superior Top-K recommendation performance without sacrificing generative strength.

Skip the bulky bidirectional teacher: this new method trains a fast, causal audio-video generator directly, slashing sampling steps while maintaining top-tier quality.