Improving Faint Object Detection for Space Situational Awareness with Variational Autoencoders
该研究使用轻量分割网络和变分自编码器结合的方法,解决了光学空间态势感知中微弱移动物体检测的问题,通过自动去星和背景重建提高检测性能。
该研究使用轻量分割网络和变分自编码器结合的方法,解决了光学空间态势感知中微弱移动物体检测的问题,通过自动去星和背景重建提高检测性能。
为解决多模态嵌入的高内存和推理成本问题,提出PUMA方法,通过后处理稀疏化技术在不重新训练主干模型的情况下生成紧凑稀疏编码,有效降低存储需求并加快检索速度。
研究通过引入自由形式指令和多模态语言接地模型StyleFlow,解决了时尚互补图像生成中用户自然查询理解和语言具体性问题。
Existing explainable AI (XAI) methods, such as SHAP, struggle to deliver explanations that are both faithful to model evidence and appropriately tailored to audiences with diverse professional backgrounds and risk sensitivities—particularly in high-stakes domains like healthcare. To address this gap, this work proposes XstrAI, the first audience-aware, multi-agent XAI narrative framework. Treating local explanations as fixed evidence, XstrAI employs three specialized LLM agents—planning, realization, and verification—that collaboratively generate customized narratives. A bounded revision loop, grounded in inconsistency detection, ensures fidelity and safety. Experiments on diabetes and stroke risk prediction tasks demonstrate that XstrAI significantly outperforms eleven baselines; its explanations are most preferred by both patients and clinicians, remain competitive among data scientists, and enable independent reviewers to accurately identify the intended audience.
This work addresses the challenge of underwater manipulator robots becoming irrecoverably stuck in confined, cluttered, and partially known environments due to limited maneuverability, narrow passages, and actuation uncertainty. To overcome this, the authors propose MANTA, a three-layer hierarchical planning and control framework that integrates topological-level global connectivity reasoning, base-arm coupled trajectory optimization, and a Gaussian process model-based reinforcement learning closed-loop controller (MC-PILCO), enabling dynamic replanning and real-time map updates. Experimental results across 120 trials demonstrate that the proposed approach significantly outperforms baseline methods in task success rate, achieves greater path clearance, reduces manipulator motion, and substantially lowers position and yaw tracking errors.
该研究使用轻量分割网络和变分自编码器结合的方法,解决了光学空间态势感知中微弱移动物体检测的问题,通过自动去星和背景重建提高检测性能。
为解决多模态嵌入的高内存和推理成本问题,提出PUMA方法,通过后处理稀疏化技术在不重新训练主干模型的情况下生成紧凑稀疏编码,有效降低存储需求并加快检索速度。
研究通过引入自由形式指令和多模态语言接地模型StyleFlow,解决了时尚互补图像生成中用户自然查询理解和语言具体性问题。
Existing explainable AI (XAI) methods, such as SHAP, struggle to deliver explanations that are both faithful to model evidence and appropriately tailored to audiences with diverse professional backgrounds and risk sensitivities—particularly in high-stakes domains like healthcare. To address this gap, this work proposes XstrAI, the first audience-aware, multi-agent XAI narrative framework. Treating local explanations as fixed evidence, XstrAI employs three specialized LLM agents—planning, realization, and verification—that collaboratively generate customized narratives. A bounded revision loop, grounded in inconsistency detection, ensures fidelity and safety. Experiments on diabetes and stroke risk prediction tasks demonstrate that XstrAI significantly outperforms eleven baselines; its explanations are most preferred by both patients and clinicians, remain competitive among data scientists, and enable independent reviewers to accurately identify the intended audience.
This work addresses the challenge of underwater manipulator robots becoming irrecoverably stuck in confined, cluttered, and partially known environments due to limited maneuverability, narrow passages, and actuation uncertainty. To overcome this, the authors propose MANTA, a three-layer hierarchical planning and control framework that integrates topological-level global connectivity reasoning, base-arm coupled trajectory optimization, and a Gaussian process model-based reinforcement learning closed-loop controller (MC-PILCO), enabling dynamic replanning and real-time map updates. Experimental results across 120 trials demonstrate that the proposed approach significantly outperforms baseline methods in task success rate, achieves greater path clearance, reduces manipulator motion, and substantially lowers position and yaw tracking errors.