Hong Yan

G2Rec captures user interest prototypes more accurately than existing methods, enabling generative recommendation systems to operate without ground-truth user interests.

Achieving 3.8x higher recall with a co-designed framework that integrates graph construction, representation learning, and real-time serving could redefine large-scale recommendation systems.

KVEraser achieves a 3-4x speedup over full recomputation while maintaining high performance in long-context tasks, revolutionizing how we handle context updates in LLMs.