2 papers
cs.AI2026
Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning
Xia Yang, Xuanyi Zhang, Hao Hu +1
Large language models now achieve high final-answer accuracy on mathematical reasoning benchmarks, but accuracy alone does not capture reasoning flexibility. We introduce a strateg…
q-bio.GN2026
Open World Knowledge Aided Single-Cell Foundation Model with Robust Cross-Modal Cell-Language Pre-training
Haoran Wang, Xuanyi Zhang, Shuangsang Fang +5
Recent advancements in single-cell multi-omics, particularly RNA-seq, have provided profound insights into cellular heterogeneity and gene regulation. While pre-trained language mo…