Dongqi Fu

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

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.

Meta's new hierarchical indexing method lets you deploy massive recommendation models without sacrificing speed or accuracy, and it turns out the index itself highlights a high-quality subset of data perfect for test-time training.