This work proposes MoR-MLLM, a computation-sparse MLLM based on the recent Mixture-of-Recursions (MoR) framework, which introduces adaptive per-token recursion, allowing the model to dynamically adjust its recursive depth and allocate more computation to visually or linguistically challenging tokens while skipping redu...
Peng-Cheng Zheng, Chao-Ning Zhang, Jia-Xing Yan et al.· 0 citations
A spatially adaptive neural operator (SANO), which replaces this spatially shared parameterization with a spatially continuous field of location-dependent operator parameters, which consistently outperforms competitive neural-operator, hypernetwork-based, and physics-informed baselines.
Jia-Quan Zhang, Chao-Ning Zhang, Shu-Xu Chen et al.· 0 citations
A budget-aware framework that systematically orchestrates when and what to teach and integrates a solvability-aware teacher gate to dictate the teacher model and a score-guided turn selection mechanism to decide what informative turns to retain is proposed.
Jian-Wei Zhang, Si-Han Cao, Peng-Cheng Zheng et al.· 0 citations
A geometry-aware incremental neural operator (GeoIncNO) for stable long-horizon PDE prediction and a mean--fluctuation decoupled reconstruction mechanism, where stable mean structures and dynamic fluctuations are fused separately, and phase correction is applied only to the zero-mean fluctuation component.
Jia-Quan Zhang, Shuxu Chen, Haifan Meng et al.· 0 citations
Experiments show that HERO consistently improves long-horizon accuracy, stable rollout length, and out-of-distribution robustness at no inference-time cost, indicating that history-enriched relative supervision is effective for stabilizing long-horizon autoregressive prediction.
