Guanglin Niu

Decoupling retrieval and reranking with a discrete diffusion model leaps ahead of monolithic embedding scorers for multi-modal knowledge graph completion.

Expression Drift can be mitigated, leading to state-of-the-art performance in text-to-image person retrieval without any training overhead.

Knowledge Graph Completion gets a boost: KGT's dedicated entity tokens and decoupled prediction heads let LLMs reason about KGs without being constrained by token fragmentation.