New ToolWorth Watching
xAIarxiv_cs_ai21 hours ago
Abstract: Computed tomography image segmentation of complex abdominal aortic aneurysms (AAA) often fails because the models assign internal focus to irrelevant ...
dissectingmodelfailures+5
ResearchImportant ResearchBreakthrough
xAIarxiv_cs_ai21 hours ago
Abstract: Explainable AI (XAI) methods are commonly evaluated with functional metrics such as correctness, which computationally estimate how accurately an explanation reflects the model's reasoning. Higher...
explanationcorrectnessmatter+5
ResearchImportant ResearchAgents & ToolsWorth Watching
xAIarxiv_cs_ai1 day ago
Abstract: Advanced Persistent Threats (APTs) are stealthy, multi-stage attacks that require adaptive and timely defense. While deep reinforcement learning (DRL) enables autonomous cyber defense, its...
deepxplainxai-guidedautonomous+5
ResearchImportant ResearchProduct Relevant
xAIarxiv_cs_cl1 day ago
Abstract: While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. Introduces Distance Ex...
explainableembeddingsdistance+1
ResearchImportant ResearchNew BenchmarkWorth Watching
xAIarxiv_cs_lg1 day ago
Abstract: Research on explainable AI (XAI) has frequently focused on explaining model predictions. More recently, methods have been proposed to explain prediction uncertainty by attributing it to input feature...