arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

AAAI Conference on Artificial Intelligence · 会议 · Artificial Intelligence

2026-03-19 至 2026-03-19 共收录 10
2603.18001 2026-03-19 cs.CV

EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding

EchoGen:基于循环一致性的统一布局-图像生成与理解学习

Kai Zou, Hongbo Liu, Dian Zheng, Jianxiong Gao, Zhiwei Zhao, Bin Liu

机构 * School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学与技术学院) Tongji University(同济大学) Sun Yat-sen University(中山大学) Fudan University(复旦大学) Hefei University of Technology(合肥工业大学) Anhui Province Key Laboratory of Digital Security(安徽省数字安全重点实验室)

AI总结 本文提出EchoGen框架,通过统一模型联合训练布局到图像生成和图像定位任务,提升生成图像的布局准确性与文本描述一致性,同时增强图像定位的鲁棒性。

Comments 9 pages, Accepted at the 40th AAAI Conference on Artificial Intelligence (AAAI 2026)

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17823 2026-03-19 cs.LG cs.CL

Discovering Decoupled Functional Modules in Large Language Models

在大型语言模型中发现解耦的功能模块

Yanke Yu, Jin Li, Ying Sun, Ping Li, Zhefeng Wang, Yi Zheng

AI总结 研究通过提出ULCMOD框架,解耦LLM中的神经元并发现输入样本的主题模块,提升模型可解释性和性能。

Comments AAAI-26 Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12224 2026-03-19 cs.CV cs.AI

Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion

在何处移动,它就重要:通过运动进行指称手术器械分割

Meng Wei, Kun Yuan, Shi Li, Yue Zhou, Long Bai, Nassir Navab, Hongliang Ren, Hong Joo Lee, Tom Vercauteren, Nicolas Padoy

AI总结 本文提出SurgRef框架,通过器械运动引导自由语言表达,实现手术视频中器械的鲁棒分割,克服遮挡和术语不熟悉问题。

Journal ref AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01310 2026-03-19 cs.LG

GraphVSSM: Graph Variational State-Space Model for Probabilistic Spatiotemporal Inference of Dynamic Exposure and Vulnerability for Regional Disaster Resilience Assessment

GraphVSSM:用于区域灾害韧性评估的图变分状态空间模型

Joshua Dimasaka, Christian Geiß, Emily So

AI总结 本文提出GraphVSSM模型,通过结合图深度学习、状态空间建模和变分推断,解决动态暴露和脆弱性评估中的时空推理问题,展示了在菲律宾、孟加拉国和塞拉利昂的案例应用,并发布了一个增强的全球静态数据集。

Comments Non-peer-reviewed Preprint | Keywords: graph state-space model, building exposure, physical vulnerability, weak supervision, probabilistic model, disaster resilience, risk audit | Code: https://github.com/riskaudit/GraphVSSM | Quezon City (Philippines) Dataset: https://doi.org/pzj2 | METEOR 2.5D Dataset, https://doi.org/pzq4, https://doi.org/pzrd | Khurushkul-Freetown Dataset: https://doi.org/pzkw

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(45): 38376-38384, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17529 2026-03-19 cs.LG cs.AI

AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

AirDDE:面向空气质量预测的多因素神经延迟微分方程

Binqing Wu, Zongjiang Shang, Shiyu Liu, Jianlong Huang, Jiahui Xu, Ling Chen

AI总结 本文提出AirDDE框架,通过引入记忆增强注意力模块和物理引导的延迟演化函数,结合多因素数据捕捉污染物传播延迟效应,实现在空气质量预测中的最优性能。

Comments AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17249 2026-03-19 cs.SI cs.CY

Information Pathways in Online Science Communication: The Role of Platform Actors and News Media

在线科学传播中的信息路径:平台参与者与新闻媒体的作用

Alexandros Efstratiou, Giuseppe Russo, Luca Luceri

AI总结 研究分析了在线科学传播中平台参与者与新闻媒体的互动,揭示了信息流动的多层级路径及协调放大结构,揭示了科学传播动态的新见解。

Comments 16 pages, 15 figures. Accepted at The 20th International AAAI Conference on Web and Social Media (ICWSM 2026). Please cite accordingly

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06129 2026-03-19 cs.SI

Rabble-Rousers in the New King's Court: Algorithmic Effects on Account Visibility in Pre-X Twitter

新国王法庭中的喧闹者:在预X推特中的算法对账号可见性的影响

Alexandros Efstratiou, Kayla Duskin, Kate Starbird, Emma Spiro

AI总结 本文研究了推特算法对账号可见性的影响,发现右倾账号在算法推荐中更受关注,而传统验证账号在算法流中曝光较少。

Comments 14 pages, 10 figures. Accepted at The 20th International AAAI Conference on Web and Social Media (ICWSM 2026). Please cite accordingly

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03369 2026-03-19 cs.CL stat.ML

Silenced Biases: The Dark Side LLMs Learned to Refuse

沉默的偏见:LLMs所学习到的拒绝的黑暗面

Rom Himelstein, Amit LeVi, Brit Youngmann, Yaniv Nemcovsky, Avi Mendelson

AI总结 本文提出Silenced Bias Benchmark,通过激活引导减少问答中的拒绝,揭示模型潜在的公平性问题,挑战传统公平评估方法。

Comments Accepted to The 40th Annual AAAI Conference on Artificial Intelligence - AI Alignment Track (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.15206 2026-03-19 cs.LG cs.AI

Conditional Distribution Learning for Graph Classification

图分类的条件分布学习

Jie Chen, Hua Mao, Chuanbin Liu, Zhu Wang, Xi Peng

机构 * College of Computer Science(计算机科学学院) Sichuan University(四川大学) Department of Computer and Information Sciences(计算机与信息科学系) Northumbria University(北安普顿大学) School of Economics and Management(经济管理学院) China University of Petroleum (Beijing)(中国石油大学(北京)) Law School(法学院)

AI总结 本文提出条件分布学习方法,通过对弱增强和强增强特征的条件分布对齐,实现图表示学习,以保留语义信息并提升图分类性能。

Comments 8 pages

Journal ref Proc. AAAI 2026, vol. 40, no. 24, pp. 20109-20117

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.00952 2026-03-19 cs.CL cs.AI

Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities

桥扩散模型:将中文文本到图像扩散模型与英文社区相结合

Shanyuan Liu, Bo Cheng, Yuhang Ma, Liebucha Wu, Ao Ma, Xiaoyu Wu, Dawei Leng, Yuhui Yin

AI总结 本文提出桥扩散模型,通过端到端结构学习中文语义并保持潜在空间与英文文本到图像模型的兼容性,实现中英文语义融合生成。

Comments Accepted as Oral at AAAI 2025. 8 pages, 5 figures. Published in Proceedings of the 39th AAAI Conference on Artificial Intelligence. Code: https://github.com/360CVGroup/Bridge_Diffusion_Model

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 39(5), 5541-5549 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏