3 papers
cs.LG2026
Silence and Noise: Resolving Suppression and Overvaluation in Multimodal Entity Alignment
Xizhe Zhang, Jingfeng Zhang, Meng-Fen Chiang
Multimodal entity alignment (MMEA) is fundamental to integrating heterogeneous knowledge graphs (KGs), yet existing paradigms remain critically vulnerable to incomplete modalities…
cond-mat.mtrl-sci2026
Deep learning driven framework for optimization of polycrystalline microstructures under competing strength requirements
Ashwini Gupta, Indrashish Saha, Lori Graham-Brady +1
Computational design of polycrystalline microstructures for enhanced mechanical performance requires repeated high-fidelity simulations over stochastic morphologies, rendering conv…
cs.RO2026
Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation
Xizhe Zhang, Jingfeng Zhang, Zirun Zhou +1
Transferring visual representations pretrained on human videos to robot manipulation requires learning reliable correspondences between human and robot demonstrations. However, pai…