Out-of-distribution (OOD) generalization in industrial Model-as-a-Service (MaaS) systems is often hindered by a trilemma of heterogeneous distribution shifts, strict inference latency budgets, and rigorous privacy constraints. Traditional robust learning and emerging foundation models frequently struggle with the entan...
Qi Qin, Yuzhao Zhang, Jiaxing Han et al.· Proceedings of the 32nd ACM...· 0 citations
Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and Real Anchoring}), a modular two-stage framework that distills TFMs into...
Multi-Dimensional Conjunctive Preference Optimization (M-DPO) is developed, which enforces simultaneous correctness across all axes and adaptively routes gradients to the most deficient dimension in post-training, bringing open scientific diagram generation close to proprietary-level structural fidelity.
