截至 2026 年 6 月，陕西省大数据知识工程重点实验室2026上半年发表（含接收）CCF-A类论文 共计 33 篇。

ICLR 2026 (2 篇 )

MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation

作者：Xirui Hu, Yanbo Ding, Jiahao Wang, Tingting Shi, Yali Wang, Guo Zhi Zhi, Weizhan Zhang合作方：中国科学院深圳先进技术研究院，TeleAI

链接：https://iclr.cc/virtual/2026/poster/10010098

AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning作者：Bowen Ping, Minnan Luo, Zhuohang Dang, Chenxi Wang, Chengyou Jia

链接：https://openreview.net/forum?id=PVtZnUh04m

ICML 2026 (2 篇 )

CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer作者：Kaixin Wang, Tianlin Li, Xiaoyu Zhang, Aishan Liu, Xianglong Liu, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, Bin Shi合作方：北京航空航天大学，南洋理工大学，蚂蚁集团，视觉信息与应用国家工程研究中心

链接：https://iclr.cc/virtual/2026/poster/10010098

Controlled Dynamics Attractor Transformer作者：Cheng Zhang, Minnan Luo, Zesheng Yang, Ming Li, Yong-Jin Liu, Qinghua Zheng

合作方：清华大学

链接：https://arxiv.org/abs/2606.15207

CVPR 2026 (6 篇 )

AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References

作者：Jiahao Wang, Hualian Sheng, Sijia Cai, Yuxiao Yang, Weizhan Zhang, Caixia Yan, Bing Deng, Jieping Ye    

合作方：阿里云计算，清华大学

链接：https://openaccess.thecvf.com/content/CVPR2026/html/Wang_AnyID_Ultra-Fidelity_Universal_Identity-Preserving_Video_Generation_from_Any_Visual_References_CVPR_2026_paper.html

Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning

作者：Rui Zhao, Bin Shi, Kai Sun, Bo Dong                                            

链接：https://openaccess.thecvf.com/content/CVPR2026/papers/Zhao_Mitigating_Instance_Entanglement_in_Instance-Dependent_Partial_Label_Learning_CVPR_2026_paper.pdf

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling

作者：Bowen Ping, Chengyou Jia, Minnan Luo, Changliang Xia, Xin Shen, Zhuohang Dang, Hangwei Qian

合作方：A*STAR

链接：https://openaccess.thecvf.com/content/CVPR2026/papers/Ping_PaCo-RL_Advancing_Reinforcement_Learning_for_Consistent_Image_Generation_with_Pairwise_CVPR_2026_paper.pdf  

SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More

作者：Muye Huang, Lingling Zhang, Yifei Li, Yaqiang Wu, Jun Liu

合作方：北京中关村学院，联想

链接：https://arxiv.org/abs/2601.05688

Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models

作者：Xinyu Zhang, Yuxuan Dong, Lingling Zhang, Chengyou Jia, Zhuohang Dang, Yixing Yao, Yaqiang Wu, Basura Fernando, Jun Liu

合作方：IHPC，联想

链接：https://openaccess.thecvf.com/content/CVPR2026/html/Zhang_Beyond_Layer-Wise_Merging_Chain-of-Merging_for_Vision-Language_Models_CVPR_2026_paper.html

Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion

作者：Bo Li, Yunkuo Lei, Tingting Bao, Hang Yan, Yaxian Wang, Weiping Fu, Lingling Zhang, Jun Liu

合作方：长安大学

链接：https://arxiv.org/abs/2509.17704

ACL 2026 (10 篇)

From What Is Said to Why It Is Framed: Intent-Aware News Video Understanding

作者：Xiangzheng Kong, Minnan Luo, Wenya Wang, Jiaying Wu, Zhi Zeng, Guang Dai  

合作方：南洋理工大学，新加坡国立大学，SGIT AI Lab

链接：https://aclanthology.org/2026.findings-acl.1945/

From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis

作者：Zhi Zeng, Jiaying Wu, Minnan Luo, Di Zhang, Yifei Yang, Xiangzheng Kong, Herun Wan, Zihan Ma

合作方：新加坡国立大学

链接：https://aclanthology.org/2026.acl-long.1716/

MUR: Momentum Uncertainty Guided Reasoning for Large Language Models

作者：Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Anh Tuan Luu, Haiteng Zhao, Qika Lin, Jun Liu

合作方：南洋理工大学，上海交通大学，温纳大学，上海人工智能实验室，新加坡国立大学

链接：https://doi.org/10.18653/v1/2026.acl-long.1058

Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents

作者：Yifei Li, Weidong Guo, Lingling Zhang, Rongman Xu, Muye Huang, Hui Liu, Lijiao Xu, Yu Xu, Jun Liu

合作方：北京中关村学院，腾讯

链接：https://doi.org/10.18653/v1/2026.acl-long.1150

GeoLaux: A Benchmark for Evaluating MLLMs’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines

作者：Yumeng Fu, Jiayin Zhu, Lingling Zhang, Wenjun Wu, Bo Zhao, Shaoxuan Ma, Yushun Zhang, Jun Liu

链接：https://doi.org/10.18653/v1/2026.acl-long.1137

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving

作者：Xinyu Zhang, Yuchen Wan, Boxuan Zhang, Zesheng Yang, Lingling Zhang, Bifan Wei, Jun Liu

链接：https://doi.org/10.18653/v1/2026.acl-long.266

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

作者：Xinyu Zhang, Boxuan Zhang, Yuchen Wan, Lingling Zhang, Yixing Yao, Bifan Wei, Yaqiang Wu, Jun Liu

合作方：联想

链接：https://doi.org/10.18653/v1/2026.findings-acl.150

AGT^AO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

作者：Pengyu Li, Lingling Zhang, Zhitao Gao, Yanrui Wu, Yuxuan Dong, Huan Liu, Bifan Wei, Jun Liu  

链接：https://doi.org/10.18653/v1/2026.findings-acl.665

MAXS: Meta-Adaptive Exploration with LLM Agents

作者：Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He, Haoran Luo, Li Yuan, Lingling Zhang, Rui Mao, Qika Lin, Jun Liu

合作方：南洋理工大学，新加坡国立大学

链接：https://doi.org/10.18653/v1/2026.findings-acl.670

PhysPRM: A Generative Process Reward Model with Fine-Grained Diagnosis for Physics Problem Solving

作者：Yuxuan Dong, Xinyu Zhang, Lingling Zhang, Han Lai, Pengyu Li, Bifan Wei, Yaqiang Wu, Jun Liu

合作方：联想

链接：https://doi.org/10.18653/v1/2026.findings-acl.458

AAAI 2026 (4 篇 )        

InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer

作者：Muyao Yuan, Yuanhong Zhang, Weizhan Zhang, Lan Ma, Yuan Gao, Jiangyong Ying, Yudeng Xin

合作方：中国电信，墨尔本大学工程与信息技术学院

链接：https://doi.org/10.1609/aaai.v40i14.38215

Enhancing Retrieval-Augmented Large Vision Language Models via Knowledge Conflict Mitigation

作者：Wenbin An, Jiahao Nie, Feng Tian, Mingxiang Cai, Yaqiang Wu, Xiaoqin Zhang, Shijian Lu

合作方：中南洋理工大学，联想，浙江工业大学

链接：https://doi.org/10.1609/aaai.v40i4.37216

MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization

作者：Jian Zhang, Zhangqi Wang, Haiping Zhu, Kangda Cheng, Kai He, Bo Li, Qika Lin, Jun Liu, Erik Cambria

合作方：哈尔滨工业大学，新加坡国立大学，南洋理工大学

链接：https://doi.org/10.1609/aaai.v40i19.38668

MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning

作者：Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Fangzhi Xu, Qika Lin, Lingling Zhang, Rui Mao, Erik Cambria, Jun Liu

合作方：新加坡国立大学，南洋理工大学

链接：https://doi.org/10.1609/aaai.v40i19.38669

WWW 2026 (1篇)

From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild

作者：Zhi Zeng, Yifei Yang, Jiaying Wu, Xulang Zhang, Xiangzheng Kong, Herun Wan, Zihan Ma, Minnan Luo

合作方：新加坡国立大学，南洋理工大学

链接：https://arxiv.org/abs/2603.25423

SIGIR 2026 (2篇)

Unifying Granularity and Reliability: A Robust and Efficient Framework for Text-based Person Retrieval

作者：Jingchen Hao, Jiang Liu, Zhen Peng, Yuting Zhang, Zhongjiang He, Weizhan Zhang, Hao Sun

合作方：中电信人工智能科技（北京）有限公司

链接：https://doi.org/10.1145/3805712.3809718

Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method

作者：Tianzhe Zhao, Jiaoyan Chen, Shuxiu Zhang, Haiping Zhu, Qika Lin, Jun Liu

合作方：曼彻斯特大学，湖南大学，新加坡国立大学

链接：https://pure.manchester.ac.uk/ws/portalfiles/portal/1885104479/SIGIR26_arxiv_1_.pdf

COLM 2026 (1 篇 )                                                                

AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback

作者：Zhitao Gao, Jie Ma, Xuhong Li, Pengyu Li, Ning Qu, Yaqiang Wu, Hui Liu, Jun Liu

合作方：联想

链接：https://arxiv.org/abs/2602.03084

IEEE Transactions on Networking (1篇)

A Concern-Decoupled Architecture for Scenario-Optimized Congestion Control in Large-Scale Live Video CDNs

作者：Danfu Yuan, Yubing Qiu, Weizhan Zhang, Mingliang Yang, Haipeng Du, Zhiwen Wang, Yiping Zhang

合作方：阿里巴巴

链接：https://ieeexplore.ieee.org/abstract/document/1133390

ACM MM (2 篇)

LLaVAFlow: Preserving Latent Alignment Flow for Parameter-Efficient Multimodal Fine-Tuning

作者：Muyao Yuan, Muyan Jiao, Jiangyong Ying, Weizhan Zhang, Yuanhong Zhang, Lan Ma, Yuan Gao, Haipeng Du

链接：https://muyaoyuan.github.io/LLaVAFlow-Page/（已接受待发表）

Uncertainty-Aware Token Disambiguation for Multimodal Sentiment Analysis with Missing Modalities

作者：Shilin Sun, Wenbin An, Qidong Liu, Zhi Zeng, Xian-Sheng Hua, Yaqiang Wu, Luyan Wang, Sibo Cai, Feng Tian

链接：已接受待发表

TMM (1篇)

Information-Theoretic Gating for Online Continual Mixture-of-Experts on Streaming Multimedia Data

作者：Xunchegn Liu, Weizhan Zhang, Tieliang Gong

Information and Computation (1  篇)

Spiking Neural P Systems Incorporating Winner-take-all Mechanism

作者：Tingting Bao, Bifan Wei, Bo Li, Lingling Zhang, Hong Peng, Xiaoqing Zhang, Jun Liu

合作方：西华大学，同济大学

链接：https://doi.org/10.1016/j.ic.2026.105472