Tag
The paper introduces a framework for personalized auto-research systems that condition every stage of the research process on individual scientist representations, arguing that personalization is essential for AI to serve as true co-scientists rather than generic instruments.
This paper proposes a unified contrastive framework for learning graph representations across multiple abstraction levels (node, proximity, cluster, graph) with a parameter-free self-weighting mechanism that adaptively assigns weights to similarity scores, outperforming state-of-the-art on downstream tasks like classification, clustering, and link prediction.