Our Research and
Publications on AI
Publications on AI
Through our research, NetMind seeks to address the most critical challenges and opportunities in AI, and to create a brighter future for humanity by unlocking the potential of AGI.
April 09 2026
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Computation and Language (cs.CL)
Yuxuan Zhang,Yubo Wang,Yipeng Zhu,Penghui Du,Junwen Miao,Xuan Lu,Wendong Xu,Yunzhuo Hao,Songcheng Cai,Xiaochen Wang,Huaisong Zhang,Xian Wu,Yi Lu,Minyi Lei,Kai Zou,Huifeng Yin,Ping Nie,Liang Chen,Dongfu Jiang,Wenhu Chen,Kelsey R. Allen
March 17 2026
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Information Retrieval (cs.IR)
Zhuofeng Li,Dongfu Jiang,Xueguang Ma,Haoxiang Zhang,Ping Nie,Yuyu Zhang,Kai Zou,Jianwen Xie,Yu Zhang,Wenhu Chen
February 10 2026
Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization
Computer Vision and Pattern Recognition (cs.CV)
Tao Yu,Yujia Yang,Haopeng Jin,Junhao Gong,Xinlong Chen,Yuxuan Zhou,Shanbin Zhang,Jiabing Yang,Xinming Wang,Hongzhu Yi,Ping Nie,Kai Zou,Zhang Zhang,Yan Huang,Liang Wang,Yeshani,Ruiwen Tao,Jin Ma,Haijin Liang,Jinwen Luo
February 05 2026
Context Forcing: Consistent Autoregressive Video Generation with Long Context
Computer Vision and Pattern Recognition (cs.CV)
Shuo Chen,Cong Wei,Sun Sun,Ping Nie,Kai Zhou,Ge Zhang,Ming-Hsuan Yang,Wenhu Chen
October 24 2025
VisCoder2: Building Multi-Language Visualization Coding Agents
Software Engineering (cs.SE)
Yuansheng Ni,Songcheng Cai,Xiangchao Chen,Jiarong Liang,Zhiheng Lyu,Jiaqi Deng,Kai Zou,Ping Nie,Fei Yuan,Xiang Yue,Wenhu Chen
September 01 2025
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
Artificial Intelligence (cs.AI)
Dongfu Jiang,Yi Lu,Zhuofeng Li,Zhiheng Lyu,Ping Nie,Haozhe Wang,Alex Su,Hui Chen,Kai Zou,Chao Du,Tianyu Pang,Wenhu Chen
February 03 2025
AceCoder: Acing Coder RL via Automated Test-Case Synthesis
Software Engineering (cs.SE)
Huaye Zeng,Dongfu Jiang,Haozhe Wang,Ping Nie,Xiaotong Chen,Wenhu Chen
June 04 2025
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Software Engineering (cs.SE)
Yuansheng Ni,Ping Nie,Kai Zou,Xiang Yue,Wenhu Chen
June 03 2025
Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
Computation and Language (cs.CL)
Yubo Wang,Ping Nie,Kai Zou,Lijun Wu,Wenhu Chen
May 21 2025
Primitive Vision: Improving Diagram Understanding in MLLMs
Computer Vision and Pattern Recognition (cs.CV)
Shan Zhang,Aotian Chen,Yanpeng Sun,Jindong Gu,Yi-Yu Zheng,Piotr Koniusz,Kai Zou,Anton Hengel,Yuan Xue
March 26 2025
Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMs
Computer Vision and Pattern Recognition (cs.CV)
Yanpeng Sun,Shan Zhang,Wei Tang,Aotian Chen,Piotr Koniusz,Kai Zou,Yuan Xue,Anton van den Hengel
March 13 2025
VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
Computer Vision and Pattern Recognition (cs.CV)
Yiming Jia,Jiachen Li,Xiang Yue,Bo Li,Ping Nie,Kai Zou,Wenhu Chen
October 08 2024
Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training
Information Retrieval (cs.IR)
Chang Su,Jiexing Qi,He Yan,Kai Zou,Zhouhan Lin
January 28 2024
A New Dataset and Method for Creativity Assessment Using the Alternate Uses Task
Communications in Computer and Information Science
Luning Sun, Hongyi Gu, Rebecca Myers and Zheng Yuan
January 11 2024
Transform-Equivariant Consistency Learning for Temporal Sentence Grounding
ACM Transactions on Multimedia Computing
Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Zichuan Xu, Haozhao Wang, Xing Di, Weining Lu and Yu Cheng
2024
ProS: Facial Omni-Representation Learning via Prototype-Based Self-Distillation
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Xing Di, Yiyu Zheng, Xiaoming Liu and Yu Cheng
2023
You Are Catching My Attention: Are Vision Transformers Bad Learners under Backdoor Attacks?
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Zenghui Yuan, Pan Zhou, Kai Zou and Yu Cheng
December 2023
Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding
Association for Computational Linguistics
Xiang Fang, Daizong Liu, Wanlong Fang, Pan Zhou, Yu Cheng, Keke Tang and Kai Zou
October 27 2023
Filling the Information Gap between Video and Query for Language-Driven Moment Retrieval
MM '23: Proceedings of the 31st ACM International Conference on Multimedia
Daizong Liu, Xiaoye Qu, Jianfeng Dong, Guoshun Nan, Pan Zhou, Zichuan Xu, Lixing Chen, He Yan and Yu Cheng
October 20 2023
Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
Computation and Language (cs.CL)
Andrea Sottana, Bin Liang, Kai Zou and Zheng Yuan
January 05, 2023
Hypotheses Tree Building for One-Shot Temporal Sentence Localization.
AAAI Conference on Artificial Intelligence (AAAI) 2023
Daizong Liu, Xiang Fang, Pan Zhou, Xing Di, Weining Lu and Yu Cheng.
January 02, 2023
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding.
Empirical Methods in Natural Language Processing (EMNLP) 2022
Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun and Zeyu Xiong.
2022
M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Advances in Neural Information Processing Systems
Hanxue Liang, Zhiwen Fan, Rishov Sarkar, Ziyu Jiang, Tianlong Chen, Kai Zou, Yu Cheng, Cong Hao and Zhangyang Wang
October 12, 2022
Local Byte Fusion for Neural Machine Translation
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Makesh Narsimhan Sreedhar, Xiangpeng Wan, Yu Cheng and Junjie Hu
December, 2022
RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL.
Empirical Methods in Natural Language Processing (EMNLP) 2022
Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang and Zhouhan Lin.
July 12, 2022
Backdoor Attacks on Crowd Counting.
ACM International Conference on Multimedia (MM) 2022
Yuhua Sun, Tailai Zhang, Pan Zhou, Zichuan Xu, Xing Di and Yu Cheng.
March, 2022
Quantifying and alleviating political bias in language models
Soroush Vosoughi Artificial Intelligence, Volume 304
Yuhua Sun, Tailai Zhang, Pan Zhou, Zichuan Xu, Xing Di and Yu Cheng.
January 14, 2022
Unsupervised Temporal Video Grounding with Deep Semantic Clustering.
AAAI Conference on Artificial Intelligence (AAAI) 2022
Daizong Liu, Xiaoye Qu, Yinzhen Wang, Xing Di, Kai Zou, Yu Cheng, Zichuan Xu and Pan Zhou
January 03, 2022
Memory-Guided Semantic Learning Network for Temporal Sentence Grounding.
AAAI Conference on Artificial Intelligence (AAAI) 2022
Daizong Liu, Xiaoye Qu, Xing Di, Yu Cheng, Zichuan Xu and Pan Zhou
March 12, 2021
Few-shot text classification with triplet networks, data augmentation, and curriculum learning.
North American Chapter of the Association of Computational Linguistics (NAACL) 2021
Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng and Shiqi Xu.
January 14, 2021
Text augmentation in a multi-task view.
European Chapter of the Association of Computational Linguistics (EACL) 2021
Jason Wei, Chengyu Huang, Shiqi Xu and Soroush Vosoughi.
January 14, 2021
Mitigating political bias in language models through reinforced calibration.
AAAI Conference on artificial intelligence (AAAI) 2021
Ruibo Liu , Chenyan Jia, Jason Wei, Guangxuan Xu, Lili Wang and Soroush Vosoughi.
November, 2020
An empirical survey of unsupervised text representation methods on twitter data.
Empirical Methods in Natural Language Processing (EMNLP) 2020
Lili Wang, Chongyang Gao, Jason Wei, Weicheng Ma, Ruibo Liu and Soroush Vosoughi.
July 2020
What Are People Asking About COVID-19? A Question Classification Dataset
Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020
Jerry Wei, Chengyu Huang, Soroush Vosoughi and Jason Wei
November, 2019
EDA: Easy Data Augmentation techniques for boosting performance on text classification tasks.
Empirical Conference on Natural Language Processing (EMNLP) 2019
Jason Wei and Kai Zou.
Transforming humanity through the power of AI