Publications
MAD-Bench: How Do Multimodal Agents Deceive You?
Hao Gu, Mingli Song, Jiacong Hu*Advances in Neural Information Processing Systems(NeurIPS)2026ProjectV-ERR: Visual Evidence Re-checking Reinforcement in Multimodal Reasoning
Hao Gu, Zhihui Yang, Hanyang Yuan, Haoze Jiang, Jiacong Hu*Underreview(Underreview)2027Causal Separation: A Theory of Representation and Recursive Self-Improvement
Zhenyu Li, Zhihui Yang, Jiacong HuUnderreview(Underreview)2026FastAdapter: Codeword-Conditioned Adapter Generation for Cross-Encoder Alignment in CSI Feedback
Xudong Zou, Jie Song, Yuanyu Wan, Zunlei Feng, Mingli Song, Jiacong Hu*Underreview(Underreview)2027CSIEval: A 6G Standard-Aligned Benchmark for AI-Based CSI Models
Shushuo Yang, Jie Song, Yuanyu Wan, Mingli Song, Jiacong Hu*Underreview(Underreview)2027Relevance Meets Spectrum: Joint Calibration For Model Merging
Yu He, Yuanyu Wan, Jiacong Hu, Jie Song, Mingli SongUnderreview(Underreview)2026Dynamic Model Merging with Multi-Layer Aggregated Routing Evidence
Yuxi Li, Yuanyu Wan, Jiacong Hu, Jie Song, Mingli SongUnderreview(Underreview)2027Improving Multimodal Reasoning via Recurrent Partitioned Evidence Reinforcement
Hao Gu, Hanyang Yuan, Haoze Jiang, Mingli Song, Jiacong Hu*Underreview(Underreview)2026Token-level Inference-Time Alignment for Vision-Language Models
Kejia Chen, Junjun Zheng, Jiawen Zhang, Manxi Lin, Xiao Pan, Jiacong Hu, Jian Lou, Zunlei Feng, Mingli SongFindings of the Association for Computational Linguistics: ACL 2026(ACL Findings)2026CodeParameter Manifold Purification
Enhancing Attention Patterns in Vision Transformers for Robustness
Yi Wang, Haofei Zhang, Hanyang Yuan, Yu Wang, Wenda Li, Haoze Jiang, Jiacong Hu, Tian Qiu, Shengxuming Zhang, Mingli Song, Jie SongAdvanced Intelligent Computing Technology and Applications(ICIC)2026Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation
Xudong Zou, Siyu Wu, Zunlei Feng, Jie Song, Yuanyu Wan, Mingli Song, Jiacong HuarXiv preprint arXiv:2607.22637(arXiv)2026CodeAn interpretable physics-informed deep learning model for estimating multiple air pollutants
Binjie Chen, Jiacong Hu, Yumiao Wang, Tian Feng, Weiwei Sun, Zunlei Feng, Gang Yang, Huiqiong WangGIScience \& Remote Sensing(GIScience \& Remote Sensing)2025Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
DenseSAM: Semantic Enhance SAM for Efficient Dense Object Segmentation
Linyun Zhou, Jiacong Hu, Shengxuming Zhang, Xiangtong Du, Mingli Song, Xiuming Zhang, Zunlei FengProceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence(IJCAI)2025CodeTree of Preferences for Diversified Recommendation
Hanyang Yuan, Ning Tang, Tongya Zheng, Jiarong Xu, Xintong Hu, Renhong Huang, Shunyu Liu, Jiacong Hu, Jiawei Chen, Mingli SongAdvances in Neural Information Processing Systems(NeurIPS)2025CodeSHAPE: Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
Kejia Chen, Jiawen Zhang, Jiacong Hu, Jiazhen Yang, Jian Lou, Zunlei Feng, Mingli SongarXiv preprint arXiv:2503.04858(arXiv)2025CodeBeyond the Label: Unveiling Fairness through Dynamic Attribute Projections in Classification
Haoze Jiang, Zunlei Feng, Jiacong Hu, Bingde Hu, Mingli Song, Yuanyu WanIEEE International Conference on Multimedia and Expo(ICME)2025Vision Mamba Mender
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
Hundredfold Accelerating for Pathological Images Diagnosis and Prognosis through Self-reform Critical Region Focusing
Xiaotian Yu, Haoming Luo, Jiacong Hu, Xiuming Zhang, Yuexuan Wang, Wenjie Liang, Yijun Bei, Mingli Song, Zunlei FengProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence(IJCAI)2024Improving Adversarial Robustness via Feature Pattern Consistency Constraint
Jiacong Hu, Jingwen Ye, Zunlei Feng, Jiazhen Yang, Shunyu Liu, Xiaotian Yu, Lingxiang Jia, Mingli SongProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence(IJCAI)2024Transformer Doctor: Diagnosing and Treating Vision Transformers
Association Pattern-aware Fusion for Biological Entity Relationship Prediction
Lingxiang Jia, Yuchen Ying, Zunlei Feng, Zipeng Zhong, Shaolun Yao, Jiacong Hu, Mingjiang Duan, Xingen Wang, Jie Song, Mingli SongAdvances in Neural Information Processing Systems(NeurIPS)2024CodeEfficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
Shengxuming Zhang, Weihan Li, Tianhong Gao, Jiacong Hu, Haoming Luo, Xiuming Zhang, Jing Zhang, Mingli Song, Zunlei FengarXiv preprint arXiv:2412.09521(arXiv)2024Deep learning based diagnosis for cysts and tumors of jaw with massive healthy samples
Dan Yu, Jiacong Hu, Zunlei Feng, Mingli Song, Huiyong ZhuScientific Reports(Scientific Reports)2022Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli SongProceedings of the AAAI Conference on Artificial Intelligence(AAAI)2022A Location Constrained Dual-branch Network for Reliable Diagnosis of Jaw Tumors and Cysts
Jiacong Hu, Zunlei Feng, Yining Mao, Jie Lei, Dan Yu, Mingli SongMedical Image Computing and Computer Assisted Intervention(MICCAI)2021