Source author record

Xuanyi Zhang

Xuanyi Zhang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Artificial Intelligence Computation and Language cond-mat.mtrl-sci cs.CY Genomics Machine Learning

Catalog footprint

What is connected

3works

6topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning

Large language models now achieve high final-answer accuracy on mathematical reasoning benchmarks, but accuracy alone does not capture reasoning flexibility. We introduce a strategy-level evaluation framework instantiated on 80 AMC 10/12 and AIME problems with 217 AoPS-derived reference strategy families. Model outputs are annotated for strategy identity, validity, and correctness using dual-AI coding with human adjudication. Across four frontier models, we find a pronounced decoupling between answer accuracy and strategy diversity. Under a single-solution prompt, all models achieve high accuracy (95%-100%), but under a multiple-strategy prompt they recover substantially fewer strategies than the human reference set. Gemini, DeepSeek, GPT, and Claude generate 184, 152, 151, and 110 distinct valid strategies, respectively, with the largest gaps in Geometry and Number Theory. The models collectively produce 50 benchmark-novel valid strategies, indicating both incomplete coverage of human strategies and some capacity for alternative reasoning. A repeated-run robustness check on 20 problems shows diminishing gains in discovered strategies, with the strongest model recovering only 39 of 55 AoPS-reference strategies (71%) after three runs. These findings position strategy diversity as a complementary dimension for evaluating mathematical reasoning beyond answer correctness.

preprint2026arXiv

Open World Knowledge Aided Single-Cell Foundation Model with Robust Cross-Modal Cell-Language Pre-training

Recent advancements in single-cell multi-omics, particularly RNA-seq, have provided profound insights into cellular heterogeneity and gene regulation. While pre-trained language model (PLM) paradigm based single-cell foundation models have shown promise, they remain constrained by insufficient integration of in-depth individual profiles and neglecting the influence of noise within multi-modal data. To address both issues, we propose an Open-world Language Knowledge-Aided Robust Single-Cell Foundation Model (OKR-CELL). It is built based on a cross-modal Cell-Language pre-training framework, which comprises two key innovations: (1) leveraging Large Language Models (LLMs) based workflow with retrieval-augmented generation (RAG) enriches cell textual descriptions using open-world knowledge; (2) devising a Cross-modal Robust Alignment (CRA) objective that incorporates sample reliability assessment, curriculum learning, and coupled momentum contrastive learning to strengthen the model's resistance to noisy data. After pretraining on 32M cell-text pairs, OKR-CELL obtains cutting-edge results across 6 evaluation tasks. Beyond standard benchmarks such as cell clustering, cell-type annotation, batch-effect correction, and few-shot annotation, the model also demonstrates superior performance in broader multi-modal applications, including zero-shot cell-type annotation and bidirectional cell-text retrieval.

preprint2022arXiv

Thickness and temperature dependence of the atomic-scale structure of SrRuO$_3$ thin films

Due to the strong lattice-property relationships which exist in complex oxide epitaxial layers, their electronic and magnetic properties can be modulated by structural distortions induced at the atomic scale. The modification and control can be affected at coherent heterointerfaces by epitaxial strain imposed by the substrate or by structural modifications to accommodate the film-substrate symmetry mismatch. Often these act in conjunction with a strong dependence on the layer thickness, especially for ultrathin layers. Moreover, as a result of these effects, the temperature dependence of the structure may deviate largely from that of the bulk. The temperature-dependent structure of 3 to 44 unit cell thick ferromagnetic SrRuO$_3$ films grown on Nb-doped SrTiO$_3$ substrates are investigated using a combination of high-resolution synchrotron X-ray diffraction and high-resolution electron microscopy. This aims to shed light on the intriguing magnetic and magnetotransport properties of epitaxial SRO layers, subjected to extensive investigations lately. The oxygen octahedral tilts and rotations are found to be strongly dependent on the temperature, the film thickness, and the distance away from the film-substrate interface. As a striking manifestation of the coupling between magnetic order and lattice structure, the Invar effect is observed below the ferromagnetic transition temperature in epitaxial layers as thin as 8 unit cells, similar to bulk ferromagnetic SrRuO$_3$.