Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs
利用知识图谱评估医疗大语言模型响应的自动事实核查
AI总结 本文提出FAITH框架，利用医学知识图谱评估医疗大语言模型响应的事实性，证明其在医疗领域具有较高的可靠性与实用性。
Comments Accepted as a conference paper at AAAI'26
期刊&会议
AAAI
AAAI Conference on Artificial Intelligence · 会议 · Artificial Intelligence
Logical Characterizations of GNNs with Mean Aggregation
具有均值聚合的GNNs的逻辑刻画
AI总结 本文研究了具有均值聚合的GNNs的表达能力，发现其在非均匀和均匀设置下分别与比值模态逻辑和无交替模态逻辑等价，且在实践中受连续性和阈值假设限制。
Comments 26 pages, extended version of paper to appear in AAAI 2026
Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
超越语义特征：用于通用AI生成图像检测的像素级映射
AI总结 本文提出通过像素级映射预处理破坏图像语义特征，提升AI生成图像检测器的跨模型泛化能力。
Comments Accepted by AAAI 2026
A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving
一种用于改进逻辑谜题求解的LLM在Answer Set Programming中的求解器循环框架
AI总结 本文提出了一种求解器循环框架，通过引导求解器进行指令微调，提升LLM在Answer Set Programming中生成逻辑谜题解答的性能。
Comments 15 pages, 7 figures, accepted at AAAI'26
Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research
现实主义与多元主义对智能的观念及其对人工智能研究的影响
AI总结 本文探讨了智能的现实主义与多元主义观念对人工智能研究的影响，指出不同观念导致方法、解释和风险评估的根本差异。
Comments The 40th Annual AAAI Conference on Artificial Intelligence, 8 pages (excl. references), 1 table
CD-DPE: Dual-Prompt Expert Network Based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution
CD-DPE：基于卷积字典特征解耦的双提示专家网络用于多对比MRI超分辨率
AI总结 CD-DPE通过双提示专家网络和卷积字典特征解耦策略，提升多对比MRI超分辨率的重建质量与泛化能力。
Comments Accepted to AAAI-2026
Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks
幻影威胁：探索和增强VLA模型对物理传感器攻击的鲁棒性
AI总结 本文提出了一种新型框架，用于研究和增强VLA模型对物理传感器攻击的鲁棒性，并开发了对抗训练方法以提升模型安全性。
Comments Accepted by AAAI 2026 main track
OptScale: Probabilistic Optimality for Inference-time Scaling
OptScale: 推断时间缩放的概率最优性
AI总结 OptScale通过概率框架和动态样本决策，提升LLMs推理性能并减少采样开销。
Comments Accepted by AAAI-2026
