Minjie Hong

Forget OCR: DocRetriever achieves state-of-the-art multimodal document retrieval by cleverly combining layout-aware sparse embeddings with a reasoning-augmented reranker.

Turns out, your image-generating diffusion model already knows how to segment anything you ask it to.

Forget hand-crafted templates: DUET learns to generate user and item profiles jointly, boosting recommendation accuracy by better aligning textual representations.