Top-Down Semantic Refinement for Image Captioning. To appear in Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
Jusheng Zhang, Kaitong Cai, Jing Yang, Jian Wang, Chengpei Tang*, Keze Wang*
LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction. To appear in Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
Jusheng Zhang, Ningyuan Liu, Yijia Fan, Zihao Huang, Qinglin Zeng, Kaitong Cai, Jian Wang, Keze Wang*
Cost-Effective Communication: An Auction-based Method for Language Agent Interaction. To appear in Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Chengpei Tang*, Jian Wang, Keze Wang*
HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution. To appear in Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
Jinzhou Tang, Jusheng Zhang, Qinhan Lv, Sidi Liu, Jing Yang, Chengpei Tang, Keze Wang*
3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale. To appear in Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Jian Wang, Keze Wang*
RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability. To appear in Annual AAAI Conference on Artificial Intelligence (AAAI), 2026. (Oral)
Kaitong Cai, Jusheng Zhang, Yijia Fan, Jing Yang, Keze Wang*
CF-VLM: CounterFactual Vision-Language Fine-tuning. In Neural Information Processing Systems (NeurIPS), 2025. [code][paper]
Jusheng Zhang, Kaitong Cai, Yijia Fan, Jian Wang, Keze Wang*
MAT-Agent: Learning to Dynamically Optimize Multi-Label Image Classification Training via Multi-Agent Collaboration. In Neural Information Processing Systems (NeurIPS), 2025. [paper]
Jusheng Zhang, Kaitong Cai, Yijia Fan, Ningyuan Liu, Keze Wang*
Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation. In Neural Information Processing Systems (NeurIPS), 2025. [paper]
Jusheng Zhang, Yijia Fan, Zimo Wen, Jian Wang, Keze Wang*
GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning. In Neural Information Processing Systems (NeurIPS), 2025. [paper]
Jusheng Zhang, Yijia Fan, Wenjun Lin, Ruiqi Chen, Haoyi Jiang, Wenhao Chai, Jian Wang, Keze Wang*
DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off. In Empirical Methods in Natural Language Processing (EMNLP), 2025. [paper]
Jusheng Zhang, Yijia Fan, Kaitong Cai, Zimeng Huang, Xiaofei Sun, Jian Wang, Chengpei Tang, Keze Wang*
Towards More Efficient Post-training via Fourier Domain Adapter Framework. In Empirical Methods in Natural Language Processing (EMNLP), 2025. [paper]
Yijia Fan, Jusheng Zhang, Keze Wang*
CCG: Rare-Label Prediction via Neural SEM–Driven Causal Game. In Empirical Methods in Natural Language Processing (EMNLP), 2025. [paper]
Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang*
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration. In Empirical Methods in Natural Language Processing (EMNLP), 2025. [paper]
Jusheng Zhang, Yijia Fan, Kaitong Cai, Xiaofei Sun, Keze Wang*
AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025. [code][paper]
Ziyi Tang, Zechuan Chen, Jiarui Yang, Jiayao Mai, Yongsen Zheng, Keze Wang*, Jinrui Chen, Liang Lin
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems. In International Conference on Machine Learning (ICML), 2025. [code][paper]
Jusheng Zhang, Zimeng Huang, Yijia Fan, Ningyuan Liu, Mingyan Li, Zhuojie Yang, Jiawei Yao, Jian Wang, Keze Wang*
Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [code][paper]
Zeqing Wang, Qingyang Ma, Wentao Wan, Haojie Li, Keze Wang*, Yonghong Tian.
SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks. In Annual AAAI Conference on Artificial Intelligence (AAAI), 2025. [code][paper]
Wentao Wan, Zhuojie Yang, Yongcan Chen, Chenglin Luo, Ruilin Wang, Kehao Cai, Nan Kang, Liang Lin, Keze Wang*.
2024
Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models. In Annual AAAI Conference on Artificial Intelligence (AAAI), 2024. [code][paper]
Qingyi Liu, Jinhui Qin, Wenxuan Ye, Hao Mou, Yuxuan He, Keze Wang*.
NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning. In Annual AAAI Conference on Artificial Intelligence (AAAI), 2024. [code][paper]
Linsheng Chen, Guangrun Wang, Liuchun Yuan, Keze Wang*, Ken Deng, Philip H.S. Torr.
Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation. In Annual AAAI Conference on Artificial Intelligence (AAAI), 2024. [code][paper]
Hui Fu, Zeqing Wang, Ke Gong, Keze Wang, Tianshui Chen, Haojie Li, Haifeng Zeng, Wenxiong Kang*.
Gesture Generation via Diffusion Model with Attention Mechanism. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024. [code]
Lingling Li, Weicong Li, Qiyuan Ding, Chengpei Tang, Keze Wang*.
2021
Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions. In Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
[paper]
Arjun Akula, Spandana Gella, Keze Wang, Song-Chun Zhu, Siva Reddy.
Solving inefficiency of self-supervised representation learning. In Proc. of International Conference on Conference on Computer Vision (ICCV), 2021.
[paper]
Guangrun Wang, Keze Wang, Guangcong Wang, Philip HS Torr, Liang Lin.
Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering. In Proc. of International Conference on Conference on Computer Vision (ICCV), 2021.
[paper]
Qingxing Cao, Wentao Wan, Keze Wang, Xiaodan Liang, Liang Lin*
Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp. In Proc. of International Conference on Robotics and Automation (ICRA), 2021. [paper][code][video]
Junfan Lin, Zhongzhan Huang, Keze Wang*, Xiaodan Liang, Weiwei Chen, Liang Lin.
2020
Grammatically Recognizing Images with Tree Convolution. In Proc. of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), 2020. [paper][code]
Guangrun Wang, Guangcong Wang, Keze Wang, Xiaodan Liang, and Liang Lin*.
2019
Adaptively Connected Neural Networks. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [paper][code]
Guangrun Wang, Keze Wang, Liang Lin*.
2018
Convolutional Memory Blocks for Depth Data Representation Learning. In Proc. of International Joint Conference on Artificial Intelligence (IJCAI), 2018. [paper]
Keze Wang, Liang Lin*, Chuangjie Ren, Wei Zhang, Wenxiu Sun.
Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[paper][ProjectPage][code][code in pytorch][Chinese Briefing]
Keze Wang, Xiaopeng Yan, Donyu Zhang, Lei Zhang, Liang Lin*.
2017
Recurrent 3D Pose Sequence Machines. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[paper][code]
Mude Lin, Liang Lin, Xiaodan Liang, Keze Wang, and Hui Cheng*.
2016
Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning. In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2016. (full paper, oral)
[paper][Dataset]
Keze Wang, Shengfu Zhai, Hui Cheng, Xiaodan Liang, and Liang Lin*.
Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[Paper]
Keze Wang, Liang Lin*, Wangmeng Zuo, Shuhang Gu, and Lei Zhang.
Local- and Holistic- Structure Preserving Image Super-Resolution via Deep Joint Component Learning. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), 2016. (oral)
[paper]
Yukai Shi, Keze Wang, Li Xu, Liang Lin*.
Learning a Lightweight Deep Convolutional Network for Joint Age and Gender Recognition. In Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), 2016. (oral)
[paper]
Linnan Zhu, Keze Wang, Liang Lin, Lei Zhang*.
2014
3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks.
In ACM International Conference on Multimedia (ACM MM), 2014. (full paper, oral)
[paper][dataset description][dataset download]
Keze Wang, Xiaolong Wang, and Liang Lin*.
2013
PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Spatial Priors. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [paper]
Keyang Shi, Keze Wang, Jiangbo Lu, and Liang Lin*.
Journal Papers
Towards Causality-Aware Inferring: A Sequential Discriminative Approach for Medical Diagnosis. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023.
[paper]
Junfan Lin, Keze Wang*, Ziliang Chen, Xiaodan Liang, Liang Lin
Multi-Person 3D Pose Estimation With Occlusion Reasoning. To appear in IEEE Transactions on Multimedia (T-MM), 2023.
[paper]
Xipeng Chen, Junzheng Zhang, Keze Wang, Pengxu Wei, Liang Lin*
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning. In IEEE Transactions on Image Processing (T-IP), 2022.
[paper]
Yang Liu, Keze Wang*, Lingbo Liu, Haoyuan Lan, Liang Lin
CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models. In iScience Cell Press Journal 2022.
[paper]
Arjun R Akula*, Keze Wang*, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Sinisa Todorovic, Joyce Chai, Song-Chun Zhu
Semantics-aware adaptive knowledge distillation for sensor-to-vision action recognition. In IEEE Transactions on Image Processing (T-IP), 2021.
[paper]
Yang Liu, Keze Wang*, Guanbin Li, Liang Lin
Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding. In IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2021.
[paper][Dataset][Chinese Media Report]
Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, Liang Lin*
3D Human Pose Machines with Self-supervised Learning. in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), vol. 42, no. 5, pp. 1069-1082, 2020.
[paper][code][ProjectPage][Media Report]
Keze Wang, Liang Lin*, Chenhan Jiang, Chen Qian, and Pengxu Wei.
Cost-Effective Object Detection: Active Sample Mining with Switchable Selection Criteria. In IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), vol. 30, no. 3, pp. 834-850, 2019.
[paper][ProjectPage][code][code in pytorch] Keze Wang, Liang Lin*, Xiaopeng Yan, Ziliang Chen, and Lei Zhang.
Active Self-Paced Learning for Cost-Effective and Progressive Face Identification. In IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), vol. 40, no. 1, pp. 7-19, 2018.
[paper][code][ProjectPage]
Liang Lin*, Keze Wang, Deyu Meng, Wangmeng Zuo, and Lei Zhang.
Cost-Effective Active Learning for Deep Image Classification. In IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), vol. 27, no. 12, pp. 2591-2600, 2017.
[paper]
Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, and Liang Lin.
Structure-Preserving Image Super-resolution via Contextualized Multi-task Learning. In IEEE Transactions on Multimedia (TMM), vol. 19, no. 12, pp. 2804-2815, 2017.
[paper][ProjectPage][Code]
Yukai Shi, Keze Wang, Chongyu Chen*, Li Xu and Liang Lin.
Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning. In IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), vol. 28, no. 10, pp. 2667-2678, 2017.
[paper][ProjectPage]
Ziliang Chen, Keze Wang, Xiao Wang, Pai Peng and Liang Lin*.
A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition. In International Journal of Computer Vision (IJCV), vol. 118, no. 2, pp. 256-273, 2016.
[paper]
Liang Lin*, Keze Wang, Wangmeng Zuo, Meng Wang, Jiebo Luo, and Lei Zhang.
PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Edge-Preserving Coherence. In IEEE Transactions on Image Processing (T-IP), vol. 24, no. 10, pp. 3019-3033, 2015.
[paper][code][ProjectPage]
Keze Wang, Liang Lin*, Jiangbo Lu, Chenglong Li, and Keyang Shi.