AAAI

Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates

使用屏障证书为自动驾驶车辆提供形式安全保证

Oumaima Barhoumi, Mohamed H Zaki, Sofiène Tahar

AI总结 本文提出一种结合屏障证书与时间到碰撞度量的形式验证安全框架，通过SMT求解器和自适应控制机制，提升自动驾驶车辆的安全性和可解释性。

Comments Accepted to AAAI-26 Bridge Program B10: Making Embodied AI Reliable with Testing and Formal Verification

EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers

EfficientFSL: 通过仅查询微调提升视觉变换器的少样本分类

Wenwen Liao, Hang Ruan, Jianbo Yu, Bing Song, YuansongWang, Xiaofeng Yang

AI总结 EfficientFSL通过仅查询微调方法，在视觉变换器中实现少样本分类的高效优化，以极小的计算开销获得优异性能。

Comments Accepted/To be presented at AAAI 2026

Information Theoretic Optimal Surveillance for Epidemic Prevalence in Networks

信息论最优监控以估计网络中的疫情流行率

Ritwick Mishra, Abhijin Adiga, Madhav Marathe, S. S. Ravi, Ravi Tandon, Anil Vullikanti

AI总结 本文提出TESTPREV问题，通过最大化互信息选择网络节点以优化疫情流行率估计，提出GREEDYMI策略在IC模型下提升互信息和减少方差。

Comments 25 pages; Added acknowledgments; In Proceedings of the AAAI 2026 Conference

Lifelong Domain Adaptive 3D Human Pose Estimation

终身领域自适应3D人体姿态估计

Qucheng Peng, Hongfei Xue, Pu Wang, Chen Chen

AI总结 本文提出了一种终身领域自适应3D人体姿态估计方法，通过生成对抗网络框架解决领域偏移和灾难性遗忘问题，提升跨域姿态估计性能。

Comments Accepted by AAAI 2026

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction

Judge Q: 用于优化KV缓存淘汰信息保留的可训练查询

Yijun Liu, Yixuan Wang, Yuzhuang Xu, Shiyu Ji, Yang Xu, Qingfu Zhu, Wanxiang Che

AI总结 Judge Q通过引入软令牌列表，优化KV缓存淘汰中的信息保留，提升解码质量与性能表现。

Comments Accepted in AAAI 2026

Unleashing Semantic and Geometric Priors for 3D Scene Completion

释放语义和几何先验以实现3D场景补全

Shiyuan Chen, Wei Sui, Bohao Zhang, Zeyd Boukhers, John See, Cong Yang

机构 * D-Robotics 纠错

AI总结 FoundationSSC通过双解耦机制和轴感知融合模块，提升3D场景补全的语义和几何指标表现。

Comments Accept by AAAI-2026

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images

美丽的图像，有毒的词语：理解并解决生成图像中的冒犯性文本

Aditya Kumar, Tom Blanchard, Adam Dziedzic, Franziska Boenisch

AI总结 本文提出了一种针对生成图像中冒犯性文本的微调策略，并发布了ToxicBench基准，用于评估和改进文本到图像模型的安全性。

Comments Accepted at AAAI 2026 (AI Alignment Track)

Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server

双域模式匹配用于从分层数据服务器中寻找视觉训练集

Yue Yao, Ruining Yang, Tom Gedeon

AI总结 本文提出双域模式匹配算法，通过分层数据服务器优化训练集搜索，提升模型在目标领域上的准确性和领域适应性。

Comments Accepted to AAAI 2026

Improving Symbolic Translation of Language Models for Logical Reasoning

提升语言模型的符号翻译以增强逻辑推理

Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine, Ehsan Shareghi

AI总结 本文通过微调和增量推理框架，提升小型语言模型在逻辑推理中的符号翻译能力，减少错误率并提高推理性能。

Comments The Third workshop of NeusymBridge @AAAI 2026 (Bridging Neurons and Symbols for NLP and Knowledge Graph Reasoning)

ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Driving

ReflexDiffusion：面向自动驾驶高侧向加速度场景的反射增强轨迹规划

Xuemei Yao, Xiao Yang, Jianbin Sun, Liuwei Xie, Xuebin Shao, Xiyu Fang, Hang Su, Kewei Yang

AI总结 ReflexDiffusion通过反射调整机制提升自动驾驶在高侧向加速度场景下的轨迹规划安全性与可靠性。

Comments Accepted by AAAI 2026

Blue Teaming Function-Calling Agents

蓝队功能调用代理

Greta Dolcetti, Giulio Zizzo, Sergio Maffeis

AI总结 该研究评估了四种开源LLM在功能调用能力下的鲁棒性，并测试了八种防御措施的有效性，发现模型存在安全隐患，防御措施尚不成熟。

Comments This work has been accepted to appear at the AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation

退火放松的投机解码用于更快的自回归图像生成

Xingyao Li, Fengzhuo Zhang, Cunxiao Du, Hui Ji

AI总结 本文提出COOL-SD，通过退火放松的投机解码方法提升自回归图像生成的速度与质量。

Comments Accepted to AAAI 2026

Pairing-free Group-level Knowledge Distillation for Robust Gastrointestinal Lesion Classification in White-Light Endoscopy

无需配对的群体级知识蒸馏用于白光内镜中胃肠道病变的鲁棒分类

Qiang Hu, Qimei Wang, Yingjie Guo, Qiang Li, Zhiwei Wang

AI总结 本文提出PaGKD，一种无需配对的群体级知识蒸馏框架，通过未配对的WLI和NBI数据实现跨模态学习，显著提升胃肠道病变分类性能。

Comments Accepted to AAAI 2026

Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback

LLM辅助同行评审的位置：通过指导与反馈解决评审缺口

JungMin Yun, JuneHyoung Kwon, MiHyeon Kim, YoungBin Kim

AI总结 本文提出通过LLM辅助指导和反馈系统解决评审缺口问题，旨在提升评审质量并促进学术生态可持续发展。

Comments Accepted to AAAI 2026 Workshop on AI for Scientific Research (AI4Research)

KTCF: Actionable Recourse in Knowledge Tracing via Counterfactual Explanations for Education

KTCF：通过反事实解释为教育中的知识追踪提供可操作的救济

Woojin Kim, Changkwon Lee, Hyeoncheol Kim

AI总结 KTCF通过反事实解释为教育中的知识追踪提供可操作的救济，提升教育AI的实用性和责任性。

Comments Accepted to AAAI-26 Special Track AI for Social Impact (oral presentation)

Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object Segmentation

小而强大：动态小波专家引导的大型模型微调用于光学遥感目标分割

Yanguang Sun, Chao Wang, Jian Yang, Lei Luo

AI总结 本文提出WEFT方法，通过动态小波专家引导微调，提升光学遥感图像目标分割性能，优于21种SOTA方法。

Comments Accepted at AAAI 2026

Gaming the Answer Matcher: Examining the Impact of Text Manipulation on Automated Judgment

利用答案匹配器：考察文本操纵对自动判断的影响

Manas Khatore, Sumana Sridharan, Kevork Sulahian, Benjamin J. Smith, Shi Feng

AI总结 研究通过测试文本操纵对自动答案匹配的影响，发现其对模型评分鲁棒，且在有参考答案时可作为替代评估方法。

Comments Accepted to the AAAI 2026 Workshop on AI Governance (AIGOV)

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation

BeDKD: 基于方向映射模块和对抗知识蒸馏的后门防御

Zhengxian Wu, Juan Wen, Wanli Peng, Yinghan Zhou, Changtong dou, Yiming Xue

AI总结 BeDKD通过方向映射模块和对抗知识蒸馏有效防御后门攻击，显著降低攻击成功率。

Journal ref AAAI 2026

Divergence-Based Similarity Function for Multi-View Contrastive Learning

基于分歧的多视图对比学习相似度函数

Jae Hyoung Jeon, Cheolsu Lim, Myungjoo Kang

机构 * Department of Mathematics, Seoul National University（首尔国立大学数学系） ； Research Institute of Mathematics, Seoul National University（首尔国立大学数学研究所） 纠错

AI总结 本文提出基于分歧的多视图对比学习相似度函数，通过分布分歧建模多视图联合结构，提升多种任务性能并提高效率。

Comments 9 pages, 5 figures. Code and Pretrained Model: https://github.com/Jeon789/DSF, v4: Removed erroneous AAAI copyright notice

Quiet Feature Learning in Algorithmic Tasks

算法任务中的安静特征学习

Prudhviraj Naidu, Zixian Wang, Leon Bergen, Ramamohan Paturi

AI总结 该研究发现，在算法任务中，模型在损失曲线平坦区域学习了对任务性能至关重要的中间特征，挑战了传统损失作为学习代理的假设。

Comments Accepted as Oral presentation @ AAAI 2026 Special Track on AI Alignment

"Hiding in Plain Sight": Designing Synthetic Dialog Generation for Uncovering Socially Situated Norms

隐于 plain sight：设计合成对话生成以揭示社会情境规范

Chengfei Wu, Dan Goldwasser

AI总结 本文提出 NormHint 数据集，通过多步骤框架生成合成对话，自动揭示社会规范，提升模型对对话中潜在规范违规的检测能力。

Comments Accepted at AAAI Workshop on Shaping Responsible Synthetic Data in the Era of Foundation Models

Can Editing LLMs Inject Harm?

能否通过编辑LLM注入危害？

Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen, Shiyang Lai, Xiongxiao Xu, Jia-Chen Gu, Jindong Gu, Huaxiu Yao, Chaowei Xiao, Xifeng Yan, William Yang Wang, Philip Torr, Dawn Song, Kai Shu

机构 * Northwestern University（西北大学） 纠错

AI总结 本文提出编辑攻击作为LLM安全威胁，揭示了通过编辑注入虚假信息和偏见的风险及高隐蔽性。

Comments Accepted to Proceedings of AAAI 2026. The first two authors contributed equally. 7 pages for main paper, 31 pages including appendix. The code, results, dataset for this paper and more resources are on the project website: https://llm-editing.github.io

Aggregating Diverse Cue Experts for AI-Generated Image Detection

聚合多样化线索专家用于AI生成图像检测

Lei Tan, Shuwei Li, Mohan Kankanhalli, Robby T. Tan

AI总结 本文提出MCAN框架，通过整合多种互补线索提升AI生成图像检测的泛化能力，实验显示在GenImage数据集上性能优于现有方法。

Comments Accepted by AAAI 2026

Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set

评估解释在拉索莫集合中区分模型的能力

Kaivalya Rawal, Eoin Delaney, Zihao Fu, Sandra Wachter, Chris Russell

AI总结 本文提出AXE方法，用于评估模型解释的质量，以区分Rashomon集合中模型的行为差异，防止虚假解释误导评估。

Comments This is a preprint of the paper published at the MURE workshop, AAAI 2026, which builds on a preprint of separate work published at FAccT 2025 (arXiv:2505.10399)

All Required, In Order: Phase-Level Evaluation for AI-Human Dialogue in Healthcare and Beyond

全部必要，按顺序：面向AI-人类对话在医疗保健及其他领域的相级评估

Shubham Kulkarni, Alexander Lyzhov, Shiva Chaitanya, Preetam Joshi

AI总结 OIP-SCE是一种用于评估AI-人类对话在医疗及其他领域中合规性的方法，通过相级证据确保临床义务按顺序满足，提升AI与临床流程的对齐度。

Comments Accepted at the AI for Medicine and Healthcare (AIMedHealth) Bridge Program, AAAI-26, Singapore. Full-length paper; to appear in Proceedings of Machine Learning Research (PMLR)

M$^2$FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting

M$^2$FMoE：多分辨率多视角频率混合专家用于极端适应时间序列预测

Yaohui Huang, Runmin Zou, Yun Wang, Laeeq Aslam, Ruipeng Dong

AI总结 M$^2$FMoE通过多分辨率多视角频率混合专家模型，有效捕捉时间序列中的常规和极端模式，提升极端事件适应性预测性能。

Comments Accepted by AAAI 2026

CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image Fusion

CtrlFuse: 基于掩码提示的可控红外与可见图像融合

Yiming Sun, Yuan Ruan, Qinghua Hu, Pengfei Zhu

AI总结 CtrlFuse通过基于掩码提示的可控融合框架，实现红外与可见图像的交互式动态融合，提升任务性能与融合质量。

Comments 18 pages,22 figures,published to AAAI 2026

How Hard Is It to Rig a Tournament When Few Players Can Beat or Be Beaten by the Favorite?

当少数玩家能击败或被 favorites 击败时，如何操纵比赛？

Zhonghao Wang, Junqiang Peng, Yuxi Liu, Mingyu Xiao

AI总结 本文研究了如何在少数玩家能击败或被 favorites 击败时操纵比赛，证明了当参数化为 v* 的入度或出度时，Tournament Fixing 问题可高效解决。

Comments Accepted by AAAI 2026

DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion

DiffMM: 一种用于准确匹配噪声和稀疏轨迹图的高效方法通过一步扩散

Chenxu Han, Sean Bin Yang, Jilin Hu

AI总结 DiffMM通过一步扩散方法，高效准确地匹配噪声和稀疏轨迹，提升交通调度和流分析的应用性能。

Comments AAAI-26

SUMMPILOT: Bridging Efficiency and Customization for Interactive Summarization System

SUMMPILOT：在交互式摘要系统中平衡效率与定制化

JungMin Yun, Juhwan Choi, Kyohoon Jin, Soojin Jang, Jinhee Jang, YoungBin Kim

AI总结 SUMMPILOT是一种通过交互式组件实现个性化摘要的系统，结合大型语言模型提升效率与定制化能力。

Comments Accepted to AAAI 2025 Demonstration Track