Comments6 pages, 1 figure, accepted at 21st International Conference on Software Engineering for Adaptive and Self-Managing Systems, April 13--14, 2026, Rio de Janeiro, Brazil
CommentsRefineStat constrains LM decoding with statistical validity checks and uses diagnostic-guided resampling (priors/likelihoods) to transform small LMs' drafts into correct, reliable probabilistic programs that can match or surpass closed-source models
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation
AdaExplore: 基于失败的适应与多样性保持搜索用于高效内核生成
Weihua Du, Jingming Zhuo, Yixin Dong, Andre Wang He, Weiwei Sun, Zeyu Zheng, Manupa Karunaratne, Ivan Fox, Tim Dettmers, Tianqi Chen, Yiming Yang, Sean Welleck
机构
*
Carnegie Mellon University(卡内基梅隆大学)
;
University of Washington(华盛顿大学)
;
Arm Ltd(Arm有限公司)
Comments15 pages, 6 tables. Introduces the Reward-Shaped Failure Hypothesis and AIRA, a deterministic inspection framework for detecting failure-untruthful patterns in AI-generated code. Includes three empirical studies and a strict matched-control replication
Stability-Weighted Decoding for Diffusion Language Models
扩散语言模型的稳定性加权解码
Yue Wu, Jian Huang
机构
*
Department of XXX, University of YYY, Location, Country(XXX系,YYY大学,Location,Country)
;
School of ZZZ, Institute of WWW, Location, Country(ZZZ学院,WWW研究所,Location,Country)
;
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, China(数据科学与人工智能系,香港理工大学,香港,中国)
AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum
AIT Academy:通过儒家三领域课程培养完整智能体
Jiaqi Li, Lvyang Zhang, Yang Zhao, Wen Lu, Lidong Zhai
机构
*
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所)
;
School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China(中国科学院大学网络安全学院)
机构
*
Department of Electrical and Computer Engineering & Ingenuity Labs, Queen’s University(电气与计算机工程系及Ingenuity实验室,女王大学)
;
Conflict Analytics Lab, Queen’s University(冲突分析实验室,女王大学)
;
Cornell Law School(康奈尔法学院)
;
Vector Institute for AI(人工智能向量研究所)