AAAI

Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers

Huiyuan Tian, Bonan Xu, Shijian Li

Comments Accepted to AAAI 2026. Camera-ready version with appendix

Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity

João Mattos, Debolina Halder Lina, Arlei Silva

Comments 12 pages, 5 figures. Accepted at AAAI-26 as an Oral

Colonel Blotto with Battlefield Games

Salam Afiouni, Jakub Cerny, Chun Kai Ling, Christian Kroer

Comments Proceedings of AAAI'26

NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling

Muhammad Usama, Mohammad Sadil Khan, Didier Stricker, Muhammad Zeshan Afzal

Comments Accepted in AAAI 2026

Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory

Yuxuan Lin, Hanjing Yan, Xuan Tong, Yang Chang, Huanzhen Wang, Ziheng Zhou, Shuyong Gao, Yan Wang, Wenqiang Zhang

机构 * AAAI Press（AAAI 压力） 纠错

Comments Accepted by AAAI 2026

Local Guidance for Configuration-Based Multi-Agent Pathfinding

Tomoki Arita, Keisuke Okumura

Comments To be presented at AAAI-26

Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation

Yanming Sun, Runzhe Zhan, Chi Seng Cheang, Han Wu, Xuebo Liu, Yuyao Niu, Fengying Ye, Kaixin Lan, Lidia S. Chao, Derek F. Wong

Comments Accepted by AAAI 2026

Realism Control One-step Diffusion for Real-World Image Super-Resolution

Zongliang Wu, Siming Zheng, Peng-Tao Jiang, Xin Yuan

机构 * Zongliang Wu 1, 2, 3（吴宗亮） ； Siming Zheng 3（郑思明） ； Peng-Tao Jiang 3（江鹏涛） ； Xin Yuan 2（袁鑫） 纠错

Comments Supplementary materials is included. The paper is accepted by AAAI 2026 (Oral). Code and models: https://zongliang-wu.github.io/RCOD-SR/

Provably data-driven projection method for quadratic programming

Anh Tuan Nguyen, Viet Anh Nguyen

机构 * TTIC 纠错

Comments Accepted to AAAI 2026

GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning

Chenglong Wang, Yongyu Mu, Hang Zhou, Yifu Huo, Ziming Zhu, Jiali Zeng, Murun Yang, Bei Li, Xiaoyang Hao, Chunliang Zhang, Fandong Meng, Jingbo Zhu, Tong Xiao

Comments Accepted by AAAI 2026

Multi-Metric Preference Alignment for Generative Speech Restoration

Junan Zhang, Xueyao Zhang, Jing Yang, Yuancheng Wang, Fan Fan, Zhizheng Wu

Comments Accepted by AAAI 2026. Demopage: https://gensr-pref.github.io

Failures to Surface Harmful Contents in Video Large Language Models

Yuxin Cao, Wei Song, Derui Wang, Jingling Xue, Jin Song Dong

Comments 12 pages, 8 figures. Accepted to AAAI 2026

Spatial Branch-and-Bound for Computing Multiplayer Nash Equilibrium

Jakub Černý, Shuvomoy Das Gupta, Christian Kroer

Comments In proceedings of AAAI'26

DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models

Yuanyuan Wang, Dongchao Yang, Yiwen Shao, Hangting Chen, Jiankun Zhao, Zhiyong Wu, Helen Meng, Xixin Wu

Comments Accepted by AAAI 2026

Understanding Dynamic Scenes in Ego Centric 4D Point Clouds

Junsheng Huang, Shengyu Hao, Bocheng Hu, Hongwei Wang, Gaoang Wang

Comments Accepted as a poster to AAAI 2026; will be published in the proceedings

Efficient and Reliable Hitting-Set Computations for the Implicit Hitting Set Approach

Hannes Ihalainen, Dieter Vandesande, André Schidler, Jeremias Berg, Bart Bogaerts, Matti Järvisalo

机构 * University of Helsinki（赫尔辛基大学） ； Vrije Universiteit Brussel（布鲁塞尔自由大学） ； KU Leuven（莱顿大学） ； University of Freiburg（弗赖堡大学） 纠错

Comments Accepted for publication in the proceedings of AAAI 2026

You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures

Shengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Zeyang Cui, Hao Chen, Yilin Xiao, Jiannong Cao, Xiao Huang

Comments This work has been accepted to AAAI'26

Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

Haorui He, Yupeng Li, Bin Benjamin Zhu, Dacheng Wen, Reynold Cheng, Francis C. M. Lau

Comments Accepted by AAAI 2026 (Oral). Code available at: https://trustworthycomp.github.io/Fact2Fiction/

MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss

Can Zhao, Pengfei Guo, Dong Yang, Yucheng Tang, Yufan He, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu

Comments Accepted by AAAI 2026

Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression

Jiameng Huang, Baijiong Lin, Guhao Feng, Jierun Chen, Di He, Lu Hou

机构 * Huawei（华为） 纠错

Comments Accepted by AAAI 2026

Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy

Buqing Nie, Yang Zhang, Rongjun Jin, Zhanxiang Cao, Huangxuan Lin, Xiaokang Yang, Yue Gao

Comments AAAI 2026 accepted

T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search

Xing Cui, Yueying Zou, Zekun Li, Peipei Li, Xinyuan Xu, Xuannan Liu, Huaibo Huang

Comments accepted by AAAI 2026 (Oral)

Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models

Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Ye Wang, Gang Tan, Shagufta Mehnaz

Comments 19 pages, 5 figures. Accepted in AAAI 2026

Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning

Fu-Yun Wang, Keqiang Sun, Yao Teng, Xihui Liu, Jiale Yuan, Jiaming Song, Hongsheng Li

Comments accepted by AAAI 2026

FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models

Hongyang Wang, Yichen Shi, Zhuofu Tao, Yuhao Gao, Liepiao Zhang, Xun Lin, Jun Feng, Xiaochen Yuan, Zitong Yu, Xiaochun Cao

Comments Accepted by AAAI 2025. Hongyang Wang and Yichen Shi contribute equally. Corresponding author: Zitong Yu

EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation

Biao Yi, Xavier Hu, Yurun Chen, Shengyu Zhang, Hongxia Yang, Fan Wu

Comments Accepted by AAAI 2026

OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding

Dianbing Xi, Jiepeng Wang, Yuanzhi Liang, Xi Qiu, Yuchi Huo, Rui Wang, Chi Zhang, Xuelong Li

Comments Accepted by AAAI 2026. Our project page: https://tele-ai.github.io/OmniVDiff/

RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence

Zengyuan Lai, Jiarui Yang, Songpengcheng Xia, Lizhou Lin, Lan Sun, Renwen Wang, Jianran Liu, Qi Wu, Ling Pei

Comments Accepted by AAAI 2026 (extended version with supplementary materials)

CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement

Chenrui Ma, Xi Xiao, Tianyang Wang, Xiao Wang, Yanning Shen

Comments Accepted by AAAI 2026

SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements

Haiyang Xie, Xi Shen, Shihua Huang, Qirui Wang, Zheng Wang

Comments Accepted by AAAI 2026. Code is available at https://ocean146.github.io/SimROD2025/