Inference in large-scale AI models is typically performed on dense parameter matrices, leading to inference cost and system complexity that scale unsustainably with model size. This limitation does not arise from insufficient model capacity, but from treating post-training inference systems as monolithic operators while ignoring internal structures formed during learning. We show that gradient update events in large models are highly localized and selective, leaving many parameter dependencies statistically indistinguishable from their initialization distribution after training. As a result, post-training inference systems are structurally non-uniform and inherently decomposable. Based on this observation, we introduce a post-training statistical criterion and a structural annealing procedure that removes unsupported dependencies and reveals stable, independent substructures. This work establishes a post-training, model-agnostic structural view of inference systems and enables structured, parallel inference without modifying model functionality or interfaces.
Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference
Human Informatics and Systems Laboratory, Doshisha University, Kyoto, Japan(大阪大学人文学与系统实验室,京都,日本);Linked Open Data Initiative, NPO, Tokyo, Japan(开放数据倡议,东京,日本);Keio Research Institute at SFC, Fujisawa, Japan(庆应义塾大学SFC研究所, Fujisawa,日本);Stroly Inc., Kyoto, Japan(Stroly公司,京都,日本)
Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate
Machine Learning Department, Carnegie Mellon University(卡内基梅隆大学机器学习系);Valence Labs;Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系)
Predictive inference for time series: why is split conformal effective despite temporal dependence?
Department of Statistics, University of Chicago(芝加哥大学统计系);Schools of Industrial and Systems Engineering and Electrical and Computer Engineering, Georgia Tech(佐治亚理工学院工业与系统工程及电气与计算机工程学院)
Revisiting Label Inference Attacks in Vertical Federated Learning: Why They Are Vulnerable and How to Defend
Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education(高可信软件技术重点实验室(北京大学));School of Computer Science, Peking University(北京大学计算机学院);Zhongguancun Laboratory, Beijing, China(中关村实验室,北京,中国)
ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering
Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore(新加坡高性能计算研究所,科技研究局);Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore(科技研究局前沿人工智能研究中心,新加坡);College of Computing and Data Science, Nanyang Technological University, Singapore(新加坡南洋理工大学计算与数据科学学院)