In-Context Learning for Robots: Methods and Applications
@article{huang2026roboticl,
title = {In-Context Learning for Robots: Methods and Applications},
author = {Huang, Haojian and
Li, Zexi and
Guo, Junhao and
Zhang, Yehang and
Peng, Wenxuan and
Zhou, Bohan and
Ruan, Weilin and
Wu, Leyi and
Wang, Chenxu and
Su, Jianchong and
Xie, Binghui and
Chen, Wosong and
Xu, Yingjie and
Zhou, Tianhao and
Chen, Suzeyu and
Zhao, Pukun and
He, Jiaqi and
Li, Xinyi and
Li, Runze and
Dong, Peiran and
Dang, Shaoxiang and
Huang, Jing and
Chen, Yingbing and
Chang, Yifan and
Zhang, Tianyi and
Deng, Shiyuan and
Wang, Haozhi and
Wei, Yangkai and
Li, Wenqian and
Yang, Han and
Zhou, Kaiwen and
Liu, Huaping and
Cheng, James and
Shao, Rui and
Wang, Donglin and
Jin, Yaochu and
Hao, Jianye and
Chen, Ying-Cong and
Li, Yinchuan},
journal = {arXiv preprint arXiv:2609.36012},
year = {2026},
eprint = {2609.36012},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2609.36012}
}
World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
@misc{zhang2026worldactionagentharnessing,
title={World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal},
author={Yehang Zhang and Haojian Huang and Yifan Chang and Jianchong Su and Bohan Zhou and Yingjie Xu and Wosong Chen and Tianhao Zhou and Chenxu Wang and Tianyi Zhang and Yangkai Wei and Wenqian Li and Shiyuan Deng and Yinchuan Li and Ying-Cong Chen and Zexi Li},
year={2026},
eprint={2609.29964},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2609.29964},
}
Agentic Generative Systems: A Survey on Autonomous Multimodal Content Creation
@article{202607.1997,
doi = {10.20944/preprints202607.1997.v1},
url = {https://doi.org/10.20944/preprints202607.1997.v1},
year = 2026,
month = {July},
publisher = {Preprints},
author = {Xinli Xu and Litao Guo and Yehang Zhang and Haotian Bai and Jiantao Lin and Jiawei Feng and Luozhou Wang and Zhen Yang and Man Chen and Zixin Zhang and Harold Haodong Chen and Chen Min and Ying-Cong Chen},
title = {Agentic Generative Systems: A Survey on Autonomous Multimodal Content Creation},
journal = {Preprints}
}
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
@misc{zhang2026worldlinesbenchmarkingmodelinglonghorizon,
title={WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents},
author={Yehang Zhang and Jianchong Su and Haojian Huang and Yifan Chang and Tianhao Zhou and Xinli Xu and Yingjie Xu and Yinchuan Li and Zexi Li and Ying-Cong Chen},
year={2026},
eprint={2606.18847},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2606.18847},
}
RSC-CoT: Visual-CoT Reasoning and Reinforced Optimization for Remote Sensing Change Captioning
@INPROCEEDINGS{11462989,
author={Zhang, Yehang and Wang, Bo and Shao, Zihang and Chen, Wosong and Zhao, Wufan},
booktitle={ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
title={RSC-CoT: Visual-Cot Reasoning and Reinforced Optimization for Remote Sensing Change Captioning},
year={2026},
volume={},
number={},
pages={11272-11276},
keywords={Satellite images;Earth Observing System;Location awareness;Protocols;Mobile communication;Communication systems;HTTP;LoRa;Wide area networks;Computer networks;Vision-language models;Remote Sensing Change Caption;Chain-of-Thought},
doi={10.1109/ICASSP55912.2026.11462989}
}
VideoMemory: Toward Consistent Video Generation via Memory Integration
@misc{zhou2026videomemoryconsistentvideogeneration,
title={VideoMemory: Toward Consistent Video Generation via Memory Integration},
author={Jinsong Zhou and Yihua Du and Xinli Xu and Luozhou Wang and Zijie Zhuang and Yehang Zhang and Shuaibo Li and Xiaojun Hu and Bolan Su and Ying-cong Chen},
year={2026},
eprint={2601.03655},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2601.03655},
}
Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis
@inproceedings{zhang-etal-2025-orchestrating,
title = "Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis",
author = "Zhang, Yehang and
Xu, Xinli and
Xu, Xiaojie and
Zhang, Doudou and
Liu, Li and
Chen, Ying-Cong",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1133/",
doi = "10.18653/v1/2025.emnlp-main.1133",
pages = "22267--22282",
ISBN = "979-8-89176-332-6",
abstract = "Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media. However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, audio diversity and the absence of dedicated datasets. While existing methods excel in short videos, they falter in long scenarios (e.g., movies) due to fragmented synthesis and inadequate cross-scene consistency. We propose LVAS-Agent, a multi-agent framework that offers a coordinated, multi-component approach to long-video audio generation. Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, audio design and audio synthesis. To enable systematic evaluation, we introduce LVAS-Bench, the first benchmark with 207 professionally curated long videos spanning diverse scenarios. Experiments show that our method outperforms state-of-the-art V2A models in overall audio synthesis quality."
}
An Enhanced XGBoost Algorithm for Mobile Price Classification
@INPROCEEDINGS{10256847,
author={Zhang, Yehang and Ding, Qi and Liu, Chao},
booktitle={2023 IEEE 6th International Conference on Big Data and Artificial Intelligence (BDAI)},
title={An Enhanced XGBoost Algorithm for Mobile Price Classification},
year={2023},
volume={},
number={},
pages={154-159},
keywords={Radio frequency;Dimensionality reduction;Filtering;Mobile handsets;Hardware;Decision trees;Optimization;XGBoost;Dung beetle optimizer (DBO);Parameter optimization;Classification},
doi={10.1109/BDAI59165.2023.10256847}
}
