武科大网讯 近日，人工智能领域国际顶尖学术会议AAAI 2026（第40届人工智能大会）论文录用结果公布。我校计算机科学与技术学院师生共有11篇高质量论文被录用，录用数量超历年总和，体现了学院在人工智能前沿研究方面的持续发展与科研实力的显著提升。
被录用的论文涵盖多个前沿研究方向，包括大语言模型与价值对齐、神经辐射场高效重建、去中心化边缘智能协同、医学图像分割、多模态鲁棒学习、低光照图像增强、行人重识别等，展现了我校师生在人工智能基础理论与关键技术创新方面取得的显著进展。
AAAI是由国际人工智能促进协会主办的年会，被中国计算机学会（CCF）推荐为A类国际学术会议，是人工智能领域公认的重要学术交流平台。AAAI 2026计划于2026年1月20日至27日在新加坡举行。本届会议共收到投稿23680篇（主赛道），经过严格的两轮双盲评审，最终录用论文4167篇，录用率相比去年降低了5.8%，录用率仅为17.6%。（计算机科学与技术学院）
附：计算机科学与技术学院AAAI 2026录用名单
序号 | 论文题目 | 教师 |
1 | MambaOVSR: Multiscale Fusion with Global Motion Modeling for Chinese Opera Video Super-Resolution | 徐新 |
2 | ICLR: Inter-Chrominance and Luminance Interaction for Natural Color Restoration in Low-Light Image Enhancement | 徐新 |
3 | Domain-Aware Suppression and Aggregation for Federated DG ReID | 徐新 |
4 | FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification | 徐新 |
5 | OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding Attacks | 鲁剑锋 |
6 | FedCure: Mitigating Participation Bias in Semi-Asynchronous Federated Learning with Non-IID Data | 鲁剑锋 |
7 | OursFed: Provable Group Fairness-Aware Federated Learning Against Distrust and Fragility | 鲁剑锋 |
8 | EccoMamba: Enhanced Cross-hierarchical Continuity Orthogonal Mamba for Medical Image Segmentation | 许俊林 |
9 | FuseMine: Robust Multi-Modal Compound-Protein Interaction Prediction via Differential Attention Feature Mining | 许俊林 |
10 | SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare Removal | 王薇 |
11 | Robust Pedestrian Detection with Uncertain Modality | 王晓 |
