AAAI

HSKBenchmark: Modeling and Benchmarking Chinese Second Language Acquisition in Large Language Models through Curriculum Tuning

HSKBenchmark: 通过课程调优建模和评估大语言模型中的中文第二语言习得

Qihao Yang, Xuelin Wang, Jiale Chen, Xuelian Dong, Yuxin Hao, Tianyong Hao

AI总结 HSKBenchmark通过课程调优构建首个中文SLA大语言模型基准，涵盖HSK 3-6级，提供教学文本、合成指令和评估系统，验证LLMs在写作和语法上的表现。

Comments Accepted by AAAI-2026

CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search

CroPS：通过跨视角正样本提升密集检索（短视频搜索）

Ao Xie, Jiahui Chen, Quanzhi Zhu, Xiaoze Jiang, Zhiheng Qin, Enyun Yu, Han Li

机构 * Kuaishou Technology（快手科技） 纠错

AI总结 CroPS通过引入多视角正样本提升短视频检索性能，减少查询重述率，已在快手搜索部署。

Comments AAAI-2026, Oral

DEPO: Dual-Efficiency Preference Optimization for LLM Agents

DEPO：用于LLM代理的双效偏好优化

Sirui Chen, Mengshi Zhao, Lei Xu, Yuying Zhao, Beier Zhu, Hanwang Zhang, Shengjie Zhao, Chaochao Lu

AI总结 DEPO通过双效偏好优化方法提升LLM代理的效率和性能，减少token和步骤消耗，同时在多个基准测试中表现优异。

Comments Accepted to AAAI 2026

ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing

Liangyu Chen, Yichen Xu, Jianzhe Ma, Yuqi Liu, Donglu Yang, Liang Zhang, Wenxuan Wang, Qin Jin

Comments Accept to AAAI 2026 Main Track

Do Large Language Models (LLMs) Understand Chronology?

Pattaraphon Kenny Wongchamcharoen, Paul Glasserman

机构 * University of California, Berkeley（加州大学伯克利分校） ； Columbia Business School（哥伦比亚大学商学院） 纠错

Comments Version 2: corrected footnote and added code repository link. Extended version of our work presented at the AAAI-26 AI4TS Workshop (poster) and AAAI-26 Student Abstract Program (oral)

MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement

Xinyue Yu, Youqing Fang, Pingyu Wu, Guoyang Ye, Wenbo Zhou, Weiming Zhang, Song Xiao

Comments Accepted to AAAI 2026

S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning

Jiangwen Dong, Zehui Lin, Wanyu Lin, Mingjin Zhang

机构 * PolyU 纠错

Comments Accepted by AAAI 2026

Core Safety Values for Provably Corrigible Agents

Aran Nayebi

机构 * Aran Nayebi（独立研究者） 纠错

Comments 14 pages. To appear in AAAI 2026 Machine Ethics Workshop (W37) Proceedings

Agent-SAMA: State-Aware Mobile Assistant

Linqiang Guo, Wei Liu, Yi Wen Heng, Tse-Hsun, Chen, Yang Wang

Comments Accepted to AAAI-26 (Main Technical Track)

Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion

Evgeniia Vu, Andrei Boiarov, Dmitry Vetrov

Comments Accepted at the 40th AAAI Conference on Artificial Intelligence (AAAI-26) Main Track

Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis

Aran Nayebi

机构 * Aran Nayebi（独立研究者） 纠错

Comments 21 pages, 1 figure, 1 table. To appear in AAAI 2026 Special Track on AI Alignment (oral)

Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs

Yang Wu, Rujing Yao, Tong Zhang, Yufei Shi, Zhuoren Jiang, Zhushan Li, Xiaozhong Liu

Comments AAAI 2026 Workshop

Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting

Junseo Koo, Jinseo Jeong, Gunhee Kim

Comments AAAI 2026

ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling

Yaxiong Chen, Qicong Wang, Chunlei Li, Jingliang Hu, Yilei Shi, Shengwu Xiong, Xiao Xiang Zhu, Lichao Mou

机构 * MedAI Technology (Wuxi) Co. Ltd.（MedAI技术（无锡）有限公司） 纠错

Comments AAAI 2026

UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space

Panqi Yang, Haodong Jing, Nanning Zheng, Yongqiang Ma

Comments Accepted by AAAI 2026,9 pages, 4 figures

Aligning Generative Music AI with Human Preferences: Methods and Challenges

Dorien Herremans, Abhinaba Roy

Comments Accepted at the AAAI-2026 Senior Member Track

Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans

Zekun Wang, Sashank Varma

Comments 11 pages, 7 figures

Journal ref AAAI 2026

Intermediate N-Gramming: Deterministic and Fast N-Grams For Large N and Large Datasets

Ryan R. Curtin, Fred Lu, Edward Raff, Priyanka Ranade

Comments AAAI 2026

MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging

Siyuan Li, Kai Yu, Anna Wang, Zicheng Liu, Chang Yu, Jingbo Zhou, Qirong Yang, Yucheng Guo, Xiaoming Zhang, Stan Z. Li

Comments AAAI 2026 (Oral Presentation) Preprint

Convex Clustering Redefined: Robust Learning with the Median of Means Estimator

Sourav De, Koustav Chowdhury, Bibhabasu Mandal, Sagar Ghosh, Swagatam Das, Debolina Paul, Saptarshi Chakraborty

机构 * Indian Statistical Institute, Kolkata（印度统计研究院，科希马） ； Department of Statistics and Data Science, University of Texas at Austin（德克萨斯大学奥斯汀分校统计与数据科学系） ； Electronics and Communication Sciences, Indian Statistical Institute, Kolkata（印度统计研究院，科希马电子与通信科学） ； Department of Statistics, University of Oxford（牛津大学统计系） ； Department of Statistics, University of Michigan（密歇根大学统计系） 纠错

Comments Accepted in AAAI 2026

ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions

Xingwei He, Qianru Zhang, Pengfei Chen, Guanhua Chen, Linlin Yu, Yuan Yuan, Siu-Ming Yiu

Comments Accepted to AAAI 2026

HiFusion: Hierarchical Intra-Spot Alignment and Regional Context Fusion for Spatial Gene Expression Prediction from Histopathology

Ziqiao Weng, Yaoyu Fang, Jiahe Qian, Xinkun Wang, Lee AD Cooper, Weidong Cai, Bo Zhou

机构 * footnotemark: 1 Corresponding author.（通讯作者） 纠错

Comments Accepted to AAAI 2026. 7 pages (main text), 12 pages total including references and supplementary material. 6 figures

Point Cloud Quantization through Multimodal Prompting for 3D Understanding

Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu, Pengfei Zhu

Comments Accepted by AAAI 2026. 11 pages, 7 figures

Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering

Xueren Ge, Sahil Murtaza, Anthony Cortez, Homa Alemzadeh

Comments Accepted by AAAI 2026

Arbitrary-Scale 3D Gaussian Super-Resolution

Huimin Zeng, Yue Bai, Yun Fu

Comments Accepted to AAAI 2026

Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation

Shiyuan Li, Yixin Liu, Qingsong Wen, Chengqi Zhang, Shirui Pan

Comments Accepted as an oral presentation by AAAI 2026

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities

Weixiang Zhao, Xingyu Sui, Jiahe Guo, Yulin Hu, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Ting Liu, Bing Qin

Comments To appear at AAAI 2026

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection

Jiangyong Yu, Changyong Shu, Sifan Zhou, Zichen Yu, Xing Hu, Yan Chen, Dawei Yang

机构 * HOUMO AI 纠错

Comments This paper is acceptted by AAAI 2026

DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy Gradients

Yuexin Bian, Jie Feng, Yuanyuan Shi

Comments The paper is accepted by AAAI 2026