arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence

2026-08-25 至 2026-08-25 共收录 5
2608.22356 2026-08-25 cs.AI cs.HC 新提交

Addressing the Selection Problem in Explainable AI

解决可解释人工智能中的选择问题

Claire Vlases, Katelyn Morrison

机构 * Carnegie Mellon University(卡内基梅隆大学)

AI总结 针对可解释人工智能(XAI)中用户难以选择合适技术的问题,研究提出多智能体大语言模型(LLM)编排工具,将用户查询转化为对应XAI解释技术,以解决选择问题。

Comments Accepted to the Workshop on Explainable Artificial Intelligence at the International Joint Conference on Artificial Intelligence 2026 (XAI@IJCAI26)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.21591 2026-08-25 cs.LG 新提交

Reaching the Tail: Calibration Diversity Drives Conformal Coverage under Data Scarcity

触及尾部:数据稀缺下校准多样性驱动保形覆盖率

Donald Aadithiyan

机构 * University of Moratuwa(莫拉图瓦大学)

AI总结 本文针对长宏观经济序列数据稀缺下的多期罕见事件预测难题,提出基于校准多样性的策略,将六个月覆盖率从67.8%提升至81.4%,并量化了诚实评分下六个月覆盖率能否达90%的待解问题。

Comments Accepted for presentation at the GlobalSouthAI D&I Workshop at IJCAI 2026, Held in Bremen Germany on 17th August 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.21582 2026-08-25 cs.LG 新提交

Reading the Room: Implicit Confusion Encoding in Recurrent World Model States

读取房间:循环世界模型状态中的隐式困惑编码

Donald Aadithiyan

机构 * University of Moratuwa(莫拉图瓦大学)

AI总结 该研究发现RSSM架构世界模型(如DreamerV3)的隐藏状态$h_t$含隐式困惑信号,经线性探针、编辑验证其因果性,该信号可在多数控制任务中泛化。

Comments Accepted for presentation at the GlobalSouthAI D&I Workshop at IJCAI 2026. Held in Bremen, Germany on the 17th August 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.22475 2026-08-25 cs.LG quant-ph 新提交

Quantum-Inspired Hybrid Neural Networks for Neural Decoding: A Controlled Ablation Study of Learnable Quantum Sidecar Integration

用于神经解码的量子启发混合神经网络:可学习量子边载集成的受控消融研究

Diana Legziel Levy, Menachem Finkelstein, Peter Chin, Eilon Vaadia, Sarel Cohen

机构 * Reichman University(赖赫曼大学) Dartmouth College(达特茅斯学院) The Hebrew University of Jerusalem(耶路撒冷希伯来大学)

AI总结 本研究通过受控消融实验,探究将PQCs作为残差边载模块集成到ResNet-50中用于神经解码的效果,发现骨干梯度训练投影的量子边载模型可提升准确率,测量引导训练能改善表征几何,且未实现量子计算优势。

Comments Accepted at the 5th International Workshop on Human Brain and Artificial Intelligence (HBAI 2026), IJCAI-ECAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.15525 2026-08-25 cs.CV cs.HC 版本更新

Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models

临床感知的合成图像生成用于胸部X光模型的概念覆盖

Amy Rafferty, Rishi Ramaesh, Ajitha Rajan

机构 * University of Edinburgh(爱丁堡大学) NHS Lothian(洛锡安国家健康服务)

AI总结 提出CARPA框架,通过解剖约束的概念扰动生成合成胸部X光图像,扩展临床概念覆盖,提升模型性能与可靠性。

Comments Accepted for presentation at the IJCAI-ECAI 2026 RobustifAI workshop

详情

展开后加载摘要…

URL PDF HTML 收藏