Heilongjiang University of Technology

An expert-level generalist AI for abdominal CT diagnosis

Artificial intelligence (AI) in radiology aspires to deliver expert-level diagnosis across diverse clinical tasks, yet existing supervised strategies remain limited in scope. We developed RADAR, a generalist vision-language model trained on more than 400,000 contrast-enhanced abd...

Continuous Mission Intelligence: An Architectural Requirement for Coherent Command Across Heterogeneous Autonomous Systems

Defense artificial intelligence has advanced quickly across four layers: operational data integration, command and control, fleet-scale coordination, and platform autonomy. This paper argues that the success of those layers has produced a distinct problem that none of them addres...

The Great Amnesia: AI Agent Memory as the Binding Constraint on Autonomous Systems in Enterprise and Defense

Frontier model capability has improved rapidly for four years while the rate at which organisations convert artificial intelligence pilots into production has not. This paper argues that the two facts are connected, and that the binding constraint is no longer reasoning quality b...

The Great Amnesia: Why the AI Industry Is Winning the Wrong Race

Every frontier laboratory is racing to make the system smarter. None is racing to make it remember. That is not a gap in the market. That is the market. Four years of capability gains have not moved the rate at which organisations put artificial intelligence into production. The...

Continuous Mission Intelligence: The Decisive Architecture for Command at Machine Speed

Defense AI has succeeded at four layers and created a fifth problem. Data integration, command and control, fleet-scale coordination and platform autonomy all work, and their success is precisely what makes the missing layer decisive. When every sensor, platform and agent is inte...

Assessment of mineralogical and chemical quantification of spodumene ore (Li) using a rapid compact XRF–XRD analyzer on-site: Impact of sample preparation on analytical results

Ore variability remains a major challenge for grade control and metallurgical performance, emphasizing the need for detailed mineralogical characterization to support process optimization and quantitative assessment of ore deportment. This study evaluates a combined XRF-XRD appro...

The Illusion of Generalization: Impact of Ultra-Low Synthetic Contamination on Deep Waveform AI Scratch Training in Acoustic Leak Detection

This paper investigates the fundamental problem of false adaptation in deep neural networks applied to non-destructive testing (NDT) of pipelines. Under severe field data shortages, developers often rely on surrogate audio files generated by rapid, heuristic methods (such as LLM-...