AAAI - arXivDaily 期刊&会议

2412.15674 2024-12-23 cs.CV

PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium

Xinzhe Li, Jiahui Zhan, Shengfeng He, Yangyang Xu, Junyu Dong, Huaidong Zhang, Yong Du

Comments This paper is accepted by AAAI 2025. The code is available at https://github.com/xzhe-Vision/PersonaMagic

2412.15650 2024-12-23 cs.LG

Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution

Wentao Tan, Qiong Cao, Yibing Zhan, Chao Xue, Changxing Ding

Comments AAAI 2025. The code is available at https://github.com/WentaoTan/SENA

2412.15623 2024-12-23 cs.CR cs.AI

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs

Hongyi Li, Jiawei Ye, Jie Wu, Tianjie Yan, Chu Wang, Zhixin Li

Comments Accepted by AAAI 2025

2412.15601 2024-12-23 cs.CV

Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation

Guanzhong Zeng, Jingjing Wang, Zefu Xu, Pengwei Yin, Wenqi Ren, Di Xie, Jiang Zhu

Comments Camera Ready. Accepted to AAAI 2025

2412.15594 2024-12-23 cs.CL

Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation

Xiaoqiang Kang, Zimu Wang, Xiaobo Jin, Wei Wang, Kaizhu Huang, Qiufeng Wang

Comments Accepted at AAAI 2025, extended version with appendix

2412.15588 2024-12-23 cs.CL

NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization

Danial Kamali, Elham J. Barezi, Parisa Kordjamshidi

Comments AAAI 2025 Project Page: https://iamdanialkamali.github.io/publication/neuro-symbolic-concept-composer

2412.15582 2024-12-23 cs.LG

A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation

Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Henry Hoffmann

Comments To appear at AAAI-25

2412.15536 2024-12-23 cs.DC cs.LG

The Impact of Cut Layer Selection in Split Federated Learning

Justin Dachille, Chao Huang, Xin Liu

Comments 16 pages, 1 figure, AAAI FLUID Workshop 2025

2412.15526 2024-12-23 cs.CV

SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation

Ke Yan, Qing Cai, Fan Zhang, Ziyan Cao, Zhi Liu

Comments Accepted by AAAI 2025

2412.15517 2024-12-23 cs.LG

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning

Yangkun Chen, Kai Yang, Jian Tao, Jiafei Lyu

Comments AAAI 2025

2412.15511 2024-12-23 cs.LG cs.AI cs.CV

RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability

Vishwesh Sangarya, Jung-Eun Kim

Comments The Annual AAAI Conference on Artificial Intelligence (AAAI), 2025

2412.15483 2024-12-23 cs.LG cs.AI cs.CV

Task-Specific Preconditioner for Cross-Domain Few-Shot Learning

Suhyun Kang, Jungwon Park, Wonseok Lee, Wonjong Rhee

Comments Accepted by AAAI 2025

2412.15461 2024-12-23 cs.GT cond-mat.dis-nn

Asymptotic Extinction in Large Coordination Games

Desmond Chan, Bart De Keijzer, Tobias Galla, Stefanos Leonardos, Carmine Ventre

Comments 21 pages, 19 figures, to be published in AAAI (Association for the Advancement of Artificial Intelligence) 2025

2412.15438 2024-12-23 cs.CV cs.AI cs.LG eess.IV

Efficient Neural Network Encoding for 3D Color Lookup Tables

Vahid Zehtab, David B. Lindell, Marcus A. Brubaker, Michael S. Brown

Comments 14 pages, 13 figures; extended version; to appear in AAAI 2025

2412.15353 2024-12-23 cs.LG cs.AI

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping

Bang An, Xun Zhou, Zirui Zhou, Ronilo Ragodos, Zenglin Xu, Jun Luo

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 39, 2025

2412.15320 2024-12-23 cs.CV

Multi-concept Model Immunization through Differentiable Model Merging

Amber Yijia Zheng, Raymond A. Yeh

Comments AAAI 2025

2412.15308 2024-12-23 cs.CL cs.IR

ViFactCheck: A New Benchmark Dataset and Methods for Multi-domain News Fact-Checking in Vietnamese

Tran Thai Hoa, Tran Quang Duy, Khanh Quoc Tran, Kiet Van Nguyen

Comments Accepted at AAAI'2025 Main Conference

2412.15306 2024-12-23 cs.CR cs.LG

MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification

Xu-Yang Chen, Lu Han, De-Chuan Zhan, Han-Jia Ye

Comments AAAI 2025 accepted

2412.15283 2024-12-23 cs.CL cs.AI cs.LG

Channel Merging: Preserving Specialization for Merged Experts

Mingyang Zhang, Jing Liu, Ganggui Ding, Xinyi Yu, Linlin Ou, Bohan Zhuang

Comments accepted by AAAI 2025

2412.12581 2024-12-23 cs.HC

Understanding Emotional Body Expressions via Large Language Models

Haifeng Lu, Jiuyi Chen, Feng Liang, Mingkui Tan, Runhao Zeng, Xiping Hu

Comments Accepted by AAAI 2025

2412.11410 2024-12-23 cs.LG

MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning

Xing Lei, Xuetao Zhang, Donglin Wang

Journal ref AAAI 2025

2412.07618 2024-12-23 cs.AI cs.CL

Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs

Xiaqiang Tang, Jian Li, Nan Du, Sihong Xie

Comments AAAI 2025

2412.07207 2024-12-23 cs.LG cs.AI cs.CL

MAPLE: A Framework for Active Preference Learning Guided by Large Language Models

Saaduddin Mahmud, Mason Nakamura, Shlomo Zilberstein

Comments AAAI 2025 AI Alignment Track

2409.16252 2024-12-23 cs.CV cs.AI cs.LG

Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation

Hannah Kerner, Snehal Chaudhari, Aninda Ghosh, Caleb Robinson, Adeel Ahmad, Eddie Choi, Nathan Jacobs, Chris Holmes, Matthias Mohr, Rahul Dodhia, Juan M. Lavista Ferres, Jennifer Marcus

Comments Accepted at the AAAI-2025 Artificial Intelligence for Social Impact (AISI) track

2409.04053 2024-12-23 cs.CV cs.AI

COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes

Koen Kraaijveld, Yifan Jiang, Kaixin Ma, Filip Ilievski

Comments 15 pages, 10 figures, accepted to AAAI-25

2408.16450 2024-12-23 cs.CV

What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer

Chaeyeon Chung, Sunghyun Park, Jeongho Kim, Jaegul Choo

Comments Accepted to AAAI 2025

2408.13741 2024-12-23 cs.CR

CAMH: Advancing Model Hijacking Attack in Machine Learning

Xing He, Jiahao Chen, Yuwen Pu, Qingming Li, Chunyi Zhou, Yingcai Wu, Jinbao Li, Shouling Ji

Comments Accepted by AAAI 2025

2406.04612 2024-12-23 cs.LG cs.AI cs.IT cs.NE cs.SI math.IT

Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint

Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin

Comments 29 pages, 14 figures, 17 tables; an extended version of our paper to be presented at the 39th AAAI Conference on Artificial Intelligence (AAAI-25) (Please cite our conference version.)

2405.19026 2024-12-23 cs.LG cs.AI cs.CL cs.CR

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

Andrew Zhao, Quentin Xu, Matthieu Lin, Shenzhi Wang, Yong-jin Liu, Zilong Zheng, Gao Huang

Comments Accepted by the 39th Annual AAAI Conference on Artificial Intelligence (AAAI-25)

2405.15332 2024-12-23 cs.LG

Cross-Validated Off-Policy Evaluation

Matej Cief, Branislav Kveton, Michal Kompan

Comments 13 pages, 7 figures, to be published in AAAI 2025