AAAI

CausalPulse: An Industrial-Grade Neurosymbolic Multi-Agent Copilot for Causal Diagnostics in Smart Manufacturing

CausalPulse：一种工业级神经符号多智能体协作者，用于智能制造中的因果诊断

Chathurangi Shyalika, Utkarshani Jaimini, Cory Henson, Amit Sheth

AI总结 CausalPulse通过神经符号架构整合异常检测、因果发现和推理，实现智能制造中的因果诊断，展现高可靠性和可扩展性。

Comments 10 pages, 8 figures, 4 tables, Accepted at AAAI-MAKE 2026 (AAAI Spring Symposium on Machine Learning and Knowledge Engineering for Knowledge-Grounded Semantic Agents)

AdaptDiff: Adaptive Guidance in Diffusion Models for Diverse and Identity-Consistent Face Synthesis (Student Abstract)

AdaptDiff: 差分模型中适应性引导以生成多样且身份一致的面部合成

Eduarda Caldeira, Tahar Chettaoui, Naser Damer, Fadi Boutros

AI总结 本文提出动态加权方案，通过适应性引导抑制无关属性，提升生成面部的一致性和多样性。

Comments Accepted at AAAI 2026 Student Abstract and Poster Program

Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths

基于离散观测独立路径的扩散过程漂移估计

Yuzhen Zhao, Yating Liu, Marc Hoffmann

AI总结 本文提出基于神经网络的非参数估计方法，用于估计扩散过程中在紧致域上的漂移函数，通过高频离散观测获得收敛率，并在高维情况下展示出优于B-样条方法的性能。

Comments Accepted for an oral presentation at the 40th Annual AAAI Conference on Artificial Intelligence (AAAI-26)

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 2026, 40(34), 28778-28785

NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification

NeoNet：一种端到端的3D MRI基于深度学习框架，用于通过生成驱动分类非侵袭性预测神经浸润

Youngung Han, Minkyung Cha, Kyeonghun Kim, Induk Um, Myeongbin Sho, Joo Young Bae, Jaewon Jung, Jung Hyeok Park, Seojun Lee, Nam-Joon Kim, Woo Kyoung Jeong, Won Jae Lee, Pa Hong, Ken Ying-Kai Liao, Hyuk-Jae Lee

机构 * Seoul National University（首尔大学） ； OUTTA ； Chung-Ang University（中央大学） ； Sookmyung Women's University（淑明女子大学） ； Samsung Medical Center, Sungkyunkwan University School of Medicine（三星医疗中心，成均馆大学医学院） ； Samsung Changwon Hospital, Sungkyunkwan University School of Medicine（三星昌原医院，成均馆大学医学院） ； NVIDIA AI Technology Center（英伟达人工智能技术中心） 纠错

AI总结 本文提出NeoNet框架，通过生成驱动分类方法预测胆管癌神经浸润，解决缺乏明确影像学标准的问题，实现最高AUC 0.7903的性能。

Comments 15 pages, 5 figures. Accepted for oral presentation at W3PHIAI Workshop, AAAI 2026

Federated Inference for Heterogeneous LLM Communication and Collaboration

联邦推断用于异构大语言模型通信与协作

Zihan Chen, Zeshen Li, Howard H. Yang, Tony Q. S. Quek, Jihong Park

AI总结 本文提出FedRefine框架，解决多LLM协作中的性能、隐私和异构性问题，通过隐私保护的KV缓存通信提升设备端推断能力。

Comments 6 pages. Accepted by AAAI 2026 Workshop on ML4Wireless

$D^2Prune$: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness

$D^2Prune$：通过双重泰勒展开和注意力分布意识对大型语言模型进行稀疏化

Lang Xiong, Ning Liu, Ao Ren, Yuheng Bai, Haining Fang, BinYan Zhang, Zhe Jiang, Yujuan Tan, Duo Liu

AI总结 本文提出$D^2Prune$方法，通过双重泰勒展开和注意力分布意识，解决现有剪枝方法在激活分布偏移和注意力模块长尾分布方面的不足，提升模型压缩效果。

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(32), 27171-27179, 2026

Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations

通过LLM赋能的反事实模拟评估在线 moderation

Giacomo Fidone, Lucia Passaro, Riccardo Guidotti

AI总结 本文提出一种基于LLM的反事实模拟方法，用于评估在线社交网络的 moderation 策略，揭示了社交传染现象及个性化策略的有效性。

Comments Accepted for publication at AAAI Conference on Artificial Intelligence 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 2026