Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain embedding retrievers collect such evidence step by step, re-encoding the question together with the passages retrieved so far, and we find that the...
Chen-Jie Qiu, Zi-Xuan Zeng, Shao-Bin Shi et al.· 0 citations
Multimodal inputs are inherently heterogeneous, not only across modalities but also in the information pathways required for effective prediction. To address this limitation, we propose InstMoE, an adaptive expert routing framework for multimodal learning. InstMoE dynamically routes each input to specialized unimodal a...
Gui-Min Hu, Xiang He, Ying-Jian Li et al.· 0 citations
The Causal Discovery Foundation Model (CDFM) is formulated as a unified, general-purpose framework for zero-shot structural inference, and a principled variational framework that treats unknown causal mechanisms as latent variables and mathematically decomposes the intractable marginal likelihood into distinct, tractab...
Jie Qiao, Ruichu Cai, Zijian Li et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.