🧑🔬 Xueqi Cheng — papers of 2026 — 11 papers, the most cited first11 papers · all years of Xueqi ChengThe Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics AnalysisAnnual Meeting of the Association for Computational Linguistics (ACL)Zihao Wei, Liang Pang, Jiahao Liu, et al.2026 · 6 citationsGated Differentiable Working Memory for Long-Context Language ModelingAnnual Meeting of the Association for Computational Linguistics (ACL)Lingrui Mei, Shenghua Liu, Yiwei Wang, et al.2026 · 4 citationsHiddenGuard: Fine-Grained Safe Generation with Specialized Representation RouterAnnual Meeting of the Association for Computational Linguistics (ACL)Lingrui Mei, Shenghua Liu, Yiwei Wang, et al.2026 · 4 citationsa1: Steep Test-time Scaling Law via Environment Augmented GenerationFindings of the Association for Computational LinguisticsLingrui Mei, Shenghua Liu, Yiwei Wang, et al.2026 · 2 citationsBeyond Dialogue Time: Temporal Semantic Memory for Personalized LLM AgentsFindings of the Association for Computational LinguisticsMiao Su, Yucan Guo, Zhongni Hou, et al.2026 · 2 citationsBaseCal: Unsupervised Confidence Calibration via Base Model SignalsAnnual Meeting of the Association for Computational Linguistics (ACL)Hexiang Tan, Wanli Yang, Junwei Zhang, et al.2026 · 1 citationIterative Structured Pruning for Large Language Models with Multi-Domain CalibrationConference of the European Chapter of the Association for Computational Linguistics (EACL)Guangxin Wu, Hao Zhang, Zhang Zhibin, et al.2026 · 1 citationDetoxification for LLM: From Dataset ItselfAnnual Meeting of the Association for Computational Linguistics (ACL)Wei Shao, Yihang Wang, Gao yu Zhu, et al.2026Distilling Large Embeddings via Hyperspherical Householder QuantizationAnnual Meeting of the Association for Computational Linguistics (ACL)Yihang Wang, Bin Wu, Yueyang Su, et al.2026Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent SystemsFindings of the Association for Computational LinguisticsZixu Wang, Bingbing Xu, Yige Yuan, et al.2026Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Yu-An Liu, Ruqing Zhang, Hongru Song, et al.2026This page in Markdown → https://md.research.elamur.ai/free/en/authors/xueqi-cheng/year/2026/