🧑🔬 Di Liang — papers of 2026 — 3 papers, the most cited first3 papers · all years of Di LiangReason Only When Needed: Efficient Generative Reward Modeling via Model-Internal UncertaintyFindings of the Association for Computational LinguisticsChao Xue, Yao Wang, Mengqiao Liu, et al.2026 · 8 citationsWhy Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Chao Xue, Yao Wang, Mengqiao Liu, et al.2026 · 6 citationsLearning from Contrasts: Synthesizing Reasoning Paths from Diverse Search TrajectoriesAnnual Meeting of the Association for Computational Linguistics (ACL)Peiyang Liu, Zhirui Chen, Xi Wang, et al.2026 · 1 citationThis page in Markdown → https://md.research.elamur.ai/free/en/authors/di-liang/year/2026/