AAAI

Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction

基于线性光谱混合和光谱-角度感知重建的知识引导掩码自编码器

Abdul Matin, Rupasree Dey, Tanjim Bin Faruk, Shrideep Pallickara, Sangmi Lee Pallickara

AI总结 本文提出一种结合物理约束的知识引导掩码自编码器，通过线性光谱混合和光谱-角度感知重建提升模型的可解释性和泛化能力。

Comments Accepted to the KGML Bridge at AAAI 2026 (non-archival)

Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models

面向推理的提示优化以对齐黑盒大语言模型

Saaduddin Mahmud, Mason Nakamura, Kyle Hollins Wray, Shlomo Zilberstein

AI总结 本文提出IAPO框架，通过联合优化提示和推理规模，提升黑盒大语言模型对齐效果。

Comments Accepted to AAAI 2026. Extended 17-page version

DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment

DR.Experts: 基于失真感知专家的差分细化方法用于盲图像质量评估

Bohan Fu, Guanyi Qin, Fazhan Zhang, Zihao Huang, Mingxuan Li, Runze Hu

AI总结 DR.Experts通过引入失真感知专家和差分细化方法，有效整合失真先验知识，提升盲图像质量评估的准确性与泛化能力。

Comments Accepted by AAAI 2026

UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment

UniFit: 向基于多模态大语言模型引导的语义对齐的通用虚拟试衣迈进

Wei Zhang, Yeying Jin, Xin Li, Yan Zhang, Xiaofeng Cong, Cong Wang, Fengcai Qiao, zhichao Lian

AI总结 UniFit通过多模态大语言模型引导的语义对齐模块，解决虚拟试衣中语义差距和数据稀缺问题，实现通用且高性能的试衣框架。

Comments accepted to AAAI-2026

HiCL: Hippocampal-Inspired Continual Learning

HiCL：基于海马体的持续学习

Kushal Kapoor, Wyatt Mackey, Yiannis Aloimonos, Xiaomin Lin

AI总结 HiCL提出了一种基于海马体的持续学习架构，通过双记忆机制和稀疏路由策略减少任务干扰，实现高效多任务学习。

Comments In proceeding of AAAI

STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision

STELAR-VISION：基于拓扑意识的高效学习以实现对齐推理

Chen Li, Han Zhang, Zhantao Yang, Fangyi Chen, Zihan Wang, Anudeepsekhar Bolimera, Marios Savvides

AI总结 STELAR-VISION通过拓扑意识训练框架提升视觉-语言模型的推理准确性和效率，实现更高效的多模态任务处理。

Comments This paper has been accepted at AAAI 2026. This is the author's extended version. The final version will appear in the official proceedings

Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents

学习代理异质群体中道德行为的动力学

Elizaveta Tennant, Stephen Hailes, Mirco Musolesi

AI总结 本文研究了在社会困境环境中，道德异质群体的学习动态，探讨了不同道德类型代理之间的相互作用及对群体行为的影响。

Comments Presented at AIES 2024 (7th AAAI/ACM Conference on AI, Ethics, and Society - San Jose, CA, USA) - see https://ojs.aaai.org/index.php/AIES/article/view/31736

Journal ref Proceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society (AIES), vol. 7, (2024), pp 1444-1454