Author

Xinling Yu

h-index 8 View on Semantic Scholar

We have 2 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design

DeepOHeat-v2 is proposed, which trains on a discretized physics loss that handles the discontinuities natively, and proposes a self-improving framework: a hotspot trust gate sends flagged placements to a reference solver, and the surrogate incrementally retrains on the refined solutions, keeping an update only when it...

Xinling Yu, Yi-Xing Li, Zi-Yue Liu et al. · 0 citations

#artificial intelligence Jun 2026

GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning

GRZO is a Group-Relative Zeroth-Order optimizer that draws one pseudo-independent perturbation per mini-batch example and aggregates the per-example losses through group-relative normalization, raising the effective gradient-direction count from one to the batch size at no additional forward cost while preserving infer...

L. Tan, Yequan Zhao, Yifan Yang et al. · arXiv.org · 0 citations