AAAI

Splats in Splats: Robust and Effective 3D Steganography towards Gaussian Splatting

Splats in Splats: 3DGS中稳健且有效的3D隐写术

Yijia Guo, Wenkai Huang, Yang Li, Gaolei Li, Hang Zhang, Liwen Hu, Jianhua Li, Tiejun Huang, Lei Ma

AI总结 splats in splats 是首个在3DGS中嵌入3D内容且不修改属性的隐写术框架，通过球谐函数加密和卷积自编码器实现高保真度与高速度的隐写术方法。

Comments Accepted by AAAI 2026

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems

代码中的阴影：探索基于LLM的多智能体软件开发系统的风险与防御

Xiaoqing Wang, Keman Huang, Bin Liang, Hongyu Li, Xiaoyong Du

AI总结 本文研究了基于LLM的多智能体软件开发系统中的安全风险，提出IMBIA攻击及Adv-IMBIA防御机制，揭示了恶意智能体对软件开发过程的威胁及防御策略。

Comments Accepted by AAAI 2026 Alignment Track

Towards Robust and Fair Next Visit Diagnosis Prediction under Noisy Clinical Notes with Large Language Models

基于大型语言模型的噪声临床笔记下的稳健与公平下次就诊诊断预测

Heejoon Koo

AI总结 本文提出基于大型语言模型的稳健与公平下次就诊诊断预测方法，通过标签缩减和分层推理策略提升预测鲁棒性和公平性。

Comments Accepted by the Association for the Advancement of Artificial Intelligence (AAAI) 2026 1st Workshop on Safe, Ethical, Certified, Uncertainty-aware, Robust, and Explainable AI for Health (SECURE-AI4H)

Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection

辅助基因学习：通过辅助基因选择进行空间基因表达估计

Kaito Shiku, Kazuya Nishimura, Shinnosuke Matsuo, Yasuhiro Kojima, Ryoma Bise

机构 * Kaito Shiku 1（东京大学） ； Kazuya Nishimura 2（东京大学） ； Shinnosuke Matsuo 1（东京大学） ； Yasuhiro Kojima 2（东京大学） ； Ryoma Bise 1（东京大学） 纠错

AI总结 本文提出辅助基因学习方法，通过利用被忽视的基因作为辅助任务提升空间基因表达估计的准确性。

Comments Accepted to Association for the Advancement of Artificial Intelligence (AAAI) 2026

Clinician-in-the-Loop Smart Home System to Detect Urinary Tract Infection Flare-Ups via Uncertainty-Aware Decision Support

临床参与的智能家庭系统：通过不确定性感知决策支持检测尿路感染复发

Chibuike E. Ugwu, Roschelle Fritz, Diane J. Cook, Janardhan Rao Doppa

AI总结 本文提出了一种临床参与的智能家庭系统，通过不确定性感知决策支持检测尿路感染复发，提升老年人慢性病管理的临床决策效果。

Comments Accepted for publication at IAAI-26 / AAAI-26

PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures

PromptMoE: 通过视觉引导的提示混合实现通用零样本异常检测

Yuheng Shao, Lizhang Wang, Changhao Li, Peixian Chen, Qinyuan Liu

AI总结 PromptMoE通过视觉引导的提示混合方法，实现了通用零样本异常检测，提升了模型对未见异常的泛化能力。

Comments 14 pages, 8 figures. Accepted to AAAI 2026

VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection

VK-Det: 基于视觉知识引导的开放词汇空域目标检测

Jianhang Yao, Yongbin Zheng, Siqi Lu, Wanying Xu, Peng Sun

AI总结 VK-Det通过视觉知识引导的原型学习方法，无需额外监督实现开放词汇空域目标检测，取得优于现有方法的检测性能。

Comments 15 pages, 8 figures, accepted by AAAI 2026

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

基于概率路径积分的可信推荐解释

Oren Barkan, Yahlly Schein, Yehonatan Elisha, Veronika Bogina, Mikhail Baklanov, Noam Koenigstein

AI总结 SPINRec通过概率路径积分技术提升推荐系统解释的保真度，通过随机基线采样实现更稳定和个性化的解释，建立了新的可解释性基准。

Journal ref AAAI 2026

Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems

在推荐系统中提取交互感知的单义概念

Dor Arviv, Yehonatan Elisha, Oren Barkan, Noam Koenigstein

AI总结 本文提出了一种在推荐系统中提取交互感知的单义概念的方法，通过稀疏自动编码器揭示潜在语义结构，实现对用户和物品嵌入之间相互作用的保持，从而支持可控的个性化。

Journal ref AAAI 2026

Modeling Retinal Ganglion Cells with Neural Differential Equations

用神经微分方程建模视网膜 ganglion 细胞

Kacper Dobek, Daniel Jankowski, Krzysztof Krawiec

机构 * Institute of Computing Science, Poznan University of Technology（计算科学研究所，波兹南技术大学） 纠错

AI总结 本文提出用神经微分方程建模视网膜 ganglion 细胞，相比传统方法在效率和适应性上更优，适用于数据有限的视觉假体应用。

Comments Accepted to the AAAI-26 Student Abstract and Poster Program, with supplementary material

SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining

SD-PSFNet: 顺序和动态点扩散函数网络用于图像去雨

Jiayu Wang, Haoyu Bian, Haoran Sun, Shaoning Zeng

AI总结 SD-PSFNet通过动态物理建模和顺序特征融合，实现了复杂场景下的高效图像去雨，取得最佳PSNR/SSIM指标。

Comments 12 pages, 7 figures, Published in AAAI 2026

Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks

多领域图预训练模型在成员推断攻击下的隐私审计

Jiayi Luo, Qingyun Sun, Yuecen Wei, Haonan Yuan, Xingcheng Fu, Jianxin Li

AI总结 针对多领域图预训练模型在成员推断攻击中的隐私风险，提出MGP-MIA框架，通过信号放大、影子模型构建和相似性推断机制提升攻击效果。

Comments Accepted by AAAI 2026(Oral)

Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models

面向图基础模型的高效、隐蔽和持久后门攻击

Jiayi Luo, Qingyun Sun, Lingjuan Lyu, Ziwei Zhang, Haonan Yuan, Xingcheng Fu, Jianxin Li

AI总结 本文提出GFM-BA，一种针对图基础模型的高效、隐蔽和持久后门攻击方法，通过无标签触发关联模块、节点自适应触发生成器和持久后门锚定模块解决后门攻击的三大挑战。

Comments Accepted by AAAI 2026

Neural Graph Navigation for Intelligent Subgraph Matching

神经图导航用于智能子图匹配

Yuchen Ying, Yiyang Dai, Wenda Li, Wenjie Huang, Rui Wang, Tongya Zheng, Yu Wang, Hanyang Yuan, Mingli Song

AI总结 NeuGN通过神经导航机制显著提升子图匹配效率，减少首次匹配步骤达98.2%

Comments Under review at AAAI 2026

PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning

PA-FAS: 向可解释和通用的多模态人脸反伪装迈进：通过路径增强强化学习

Yingjie Ma, Xun Lin, Yong Xu, Weicheng Xie, Zitong Yu

AI总结 PA-FAS通过路径增强强化学习提升多模态人脸反伪装的可解释性和泛化能力。

Comments Accepted by AAAI 2026 (Oral)

Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds

具有可证明可控学习界限的成本敏感符合训练

Xuesong Jia, Yuanjie Shi, Ziquan Liu, Yi Xu, Yan Yan

AI总结 本文提出一种成本敏感符合训练算法，通过排名加权策略有效控制学习界限，实验表明其在预测效率上优于现有方法，平均预测集大小减少21.38%。

Comments Accepted for Publication at Association for the Advancement of Artificial Intelligence (AAAI), 2026

A superpersuasive autonomous policy debating system

一种超级有说服力的自主辩论系统

Allen Roush, Devin Gonier, John Hines, Judah Goldfeder, Philippe Martin Wyder, Sanjay Basu, Ravid Shwartz Ziv

AI总结 DeepDebater是一种能够自主参与并赢得完整政策辩论的AI系统，通过多智能体协作生成高质量论证并战胜人类对手。

Comments Accepted to CLIP workshop at AAAI 2026

A Hybrid Classical-Quantum Fine Tuned BERT for Text Classification

一种混合的经典-量子微调BERT用于文本分类

Abu Kaisar Mohammad Masum, Naveed Mahmud, M. Hassan Najafi, Sercan Aygun

AI总结 本文提出一种结合量子电路和经典BERT的混合模型，用于提升文本分类性能，实验表明其在多个基准数据集上表现优异。

Comments This paper has been accepted by First AAAI Symposium on Quantum Information & Machine Learning (QIML): Bridging Quantum Computing and Artificial Intelligence at AAAI 2025 Fall Symposium

TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin

TTF: 一种用于抖音LTV预测的梯形时间融合框架

Yibing Wan, Zhengxiong Guan, Chaoli Zhang, Xiaoyang Li, Lai Xu, Beibei Jia, Zhenzhe Zheng, Fan Wu

机构 * Douyin Group（抖音集团） 纠错

AI总结 TTF框架通过梯形多时间序列模块和MT-FusionNet结构，解决LTV预测中的数据不匹配、SILO挑战和序列非平稳问题，提升预测精度。

Comments Accepted by AAAI IAAI Track

Journal ref AAAI 2026 IAAI Track

BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?

BD-Net: 卷积深度学习中是否曾应用于二进制神经网络？

DoYoung Kim, Jin-Seop Lee, Noo-ri Kim, SungJoon Lee, Jee-Hyong Lee

AI总结 BD-Net通过1.58位卷积和预BN残差连接，首次实现了二进制神经网络中深度卷积的二值化，在多个数据集上取得显著准确率提升。

Comments Paper accepted to AAAI 2026

Enhanced Federated Deep Multi-View Clustering under Uncertainty Scenario

不确定场景下的增强联邦深度多视图聚类

Bingjun Wei, Xuemei Cao, Jiafen Liu, Haoyang Liang, Xin Yang

AI总结 本文提出EFDMVC框架，通过语义对齐、视图自适应漂移和平衡聚合机制，解决联邦多视图聚类中的视图不确定性和聚合不确定性问题，实验验证其在异构不确定视图下的鲁棒性。

Journal ref AAAI 2026

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

CompTrack: 基于信息瓶颈的点云跟踪低秩动态令牌压缩

Sifan Zhou, Yichao Cao, Jiahao Nie, Yuqian Fu, Ziyu Zhao, Xiaobo Lu, Shuo Wang

AI总结 CompTrack通过信息瓶颈引导的低秩动态令牌压缩技术，有效解决点云中空间和信息冗余问题，实现高效实时的三维单目标跟踪。

Comments Accepted by AAAI 2026 (Oral)

Multi-Aspect Cross-modal Quantization for Generative Recommendation

多方面跨模态量化用于生成性推荐

Fuwei Zhang, Xiaoyu Liu, Dongbo Xi, Jishen Yin, Huan Chen, Peng Yan, Fuzhen Zhuang, Zhao Zhang

AI总结 MACRec通过多方面跨模态量化方法，提升生成性推荐中多模态信息利用和语义ID学习的性能。

Comments Accepted by AAAI 2026 (Oral)

Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries

基于测试时间校准的双动态字典图域外分布检测

Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu

AI总结 BaCa通过双动态字典校准测试时间图域外分布检测，无需微调预训练模型，有效提升OOD检测性能。

Comments Accepted by AAAI 2026 (The 40th Annual AAAI Conference on Artificial Intelligence)

ComLQ: Benchmarking Complex Logical Queries in Information Retrieval

ComLQ：信息检索中复杂逻辑查询的基准测试

Ganlin Xu, Zhitao Yin, Linghao Zhang, Jiaqing Liang, Weijia Lu, Xiaodong Zhang, Zhifei Yang, Sihang Jiang, Deqing Yang

AI总结 ComLQ通过构建包含2909个查询和11251个候选段落的信息检索数据集，提出Log-Scaled Negation Consistency指标，评估检索模型在复杂逻辑查询，特别是含否定查询上的性能。

Comments Accepted by AAAI 2026

Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion

超越表面遗忘：通过知识密度估计和块重新插入实现彻底遗忘

Feng Guo, Yuntao Wen, Shen Gao, Junshuo Zhang, Shuo Shang

AI总结 KUnBR通过知识密度估计和块重新插入策略，有效解决大语言模型中有害知识的彻底移除问题，实现高效的遗忘与模型实用性平衡。

Comments Accepted by AAAI 2026

DeepRWCap: Neural-Guided Random-Walk Capacitance Solver for IC Design

DeepRWCap：基于神经网络的随机游走电容求解器用于集成电路设计

Hector R. Rodriguez, Jiechen Huang, Wenjian Yu

AI总结 DeepRWCap通过神经网络引导随机游走求解器，提高集成电路设计中电容计算的精度与效率。

Comments Accepted to AAAI-26

Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models

针对多模态语言模型的红队测试：评估不同提示模态和模型的有害性

Madison Van Doren, Casey Ford

AI总结 本研究通过红队测试评估多模态语言模型在不同提示模态下的安全性，发现Pixtral 12B的有害响应率最高，而Claude Sonnet 3.5最安全，凸显了建立多模态安全基准的必要性。

Journal ref AAAI 2026 AIGOV Workshop and EurIPS 2025 Workshop on Unifying Perspectives on Learning Biases

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation

SpecDiff: 通过自推测加速扩散模型推理

Jiayi Pan, Jiaming Xu, Yongkang Zhou, Guohao Dai

AI总结 SpecDiff通过自推测引入未来信息，提出无需训练的多级特征缓存策略，实现扩散模型推理的高效加速。

Comments Accepted by AAAI 2026 Oral

Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments

Tapas Are Free! 通过LLM引导的程序合成实现动态环境下的免训练程序代理适应

Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang

AI总结 TAPA通过LLM引导的程序合成，在动态环境中实现免训练的程序代理适应，提升网络安全和群体智能任务的性能与可靠性。

Comments Extended version of the paper accepted at AAAI-26 Oral to comply with the AAAI camera-ready requirements with minor revisions