Shiyu Huang   黄世宇

@misc{yu2026groundingpigroundingfoundationmodel,
    title={GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives},
    author={Qize Yu and Lianrui Fan and Boyu Chen and Jiaqi Liang and Xini Ding and Yue Chen and Zetian Song and Yuran Wang and Yi Zou and Kaixuan Wang and Tianxing Chen and Wenxuan Song and Bohan Zhou and Mingleyang Li and Siqiao Huang and Yuqi Ye and Caigao Jiang and Wei Wei and Ruihai Wu and Hang Zhang and Yixiao Ge and Shuchang Zhou and Shilong Liu and Xianming Liu and Ping Luo and Shiyu Huang},
    year={2026},
    eprint={2609.39601},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2609.39601},
}

@misc{yu2026groundanythingreconcilingparalleldecoding,
    title={GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed},
    author={Qize Yu and Lianrui Fan and Bowen Ping and Xini Ding and Zetian Song and Junbo Niu and Kaixuan Wang and Tianxing Chen and Yue Chen and Minghua He and Yuran Wang and Jie Huang and Haojun Zhang and Min Chen and Hao Li and Wenxuan Song and Ruihai Wu and Xianming Liu and Shilong Liu and Shuchang Zhou and Ping Luo and Shiyu Huang},
    year={2026},
    eprint={2609.39600},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2609.39600},
}

@misc{ye2026augustusautonomousdrivingvlamodel,
    title={AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding},
    author={Yuqi Ye and Caigao Jiang and Zhuonan Wang and Congyuan Pei and Chao Qu and Changhao Peng and Junhong Lin and Qize Yu and Zetian Song and Guangzhao Fu and Chongruo Wu and Shiyu Huang and Shuchang Zhou and Honggou Yang and Wei Gao},
    year={2026},
    eprint={2610.16985},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2610.16985},
}

@misc{zhang2026xautprogressiveaudioencodercompression,
    title={X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation},
    author={Haojun Zhang and Yi Zou and Min Chen and Qize Yu and Lianrui Fan and Xini Ding and Hao Li and Shuchang Zhou and
    Xianming Liu and Shiyu Huang},
    year={2026},
    eprint={2609.11412},
    archivePrefix={arXiv},
    primaryClass={cs.SD},
    url={https://arxiv.org/abs/2609.11412},
}

@article{henry2026omnigui,
    title={OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments},
    author={Henry, Felix and Lin, Xiaochen and Zhu, Jiangyou and Zhang, Bingqian and Chen, Min and Huang, Shiyu and others},
    journal={arXiv preprint arXiv:2605.18758},
    year={2026}
}

@article{chen2025omnidpo,
  title={OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination},
  author={Chen, Junzhe and Zhang, Tianshu and Huang, Shiyu and Niu, Yuwei and Sun, Chao and Zhang, Rongzhou and Zhou, Guanyu and Wen, Lijie and Hu, Xuming},
  journal={arXiv preprint arXiv:2509.00723},
  year={2025}
}

@misc{pan2025omnisafetybenchbenchmarksafetyevaluation,
      title={Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models},
      author={Leyi Pan and Zheyu Fu and Yunpeng Zhai and Shuchang Tao and Sheng Guan and Shiyu Huang and Lingzhe Zhang and Zhaoyang Liu and Bolin Ding and Felix Henry and Lijie Wen and Aiwei Liu},
      year={2025},
      eprint={2508.07173},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.07173},
}

@article{bie2025omniplay,
  title={OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing},
  author={Bie, Fuqing and Huang, Shiyu and Tao, Xijia and Fang, Zhiqin and Pan, Leyi and Chen, Junzhe and Ren, Min and Xiang, Liuyu and He, Zhaofeng},
  journal={arXiv preprint arXiv:2508.04361},
  year={2025}
}

@article{cai2025sa,
  title={SA-GCS: Semantic-Aware Gaussian Curriculum Scheduling for UAV Vision-Language Navigation},
  author={Cai, Hengxing and Dong, Jinhan and Rao, Yijie and Deng, Jingcheng and Tan, Jingjun and Chen, Qien and Wang, Haidong and Wang, Zhen and Huang, Shiyu and Sumalee, Agachai and others},
  journal={arXiv preprint arXiv:2508.00390},
  year={2025}
}

@article{hong2025glm,
  title={GLM-4.1 V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning},
  author={Hong, Wenyi and Yu, Wenmeng and Gu, Xiaotao and Wang, Guo and Gan, Guobing and Tang, Haomiao and Cheng, Jiale and Qi, Ji and Ji, Junhui and Pan, Lihang and others},
  journal={arXiv preprint arXiv:2507.01006},
  year={2025}
}

@article{wang2025generalizable,
  title={Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation},
  author={Wang, Chenxu and Jin, Yonggang and Hu, Cheng and Zhao, Youpeng and Dai, Zipeng and Zhao, Jian and Xiang, Liuyu and Zhang, Junge and He, Zhaofeng},
  journal={Neurocomputing},
  pages={130912},
  year={2025},
  publisher={Elsevier}
}

@article{hong2025motionbench,
  title={MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models},
  author={Hong, Wenyi and Cheng, Yean and Yang, Zhuoyi and Wang, Weihan and Wang, Lefan and Gu, Xiaotao and Huang, Shiyu and Dong, Yuxiao and Tang, Jie},
  journal={arXiv preprint arXiv:2501.02955},
  year={2025}
}

@article{xu2024visionreward,
  title={VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation},
  author={Xu, Jiazheng and Huang, Yu and Cheng, Jiale and Yang, Yuanming and Xu, Jiajun and Wang, Yuan and Duan, Wenbo and Yang, Shen and Jin, Qunlin and Li, Shurun and others},
  journal={arXiv preprint arXiv:2412.21059},
  year={2024}
}

@article{chen2024ict,
  title={ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models},
  author={Chen, Junzhe and Zhang, Tianshu and Huang, Shiyu and Niu, Yuwei and Zhang, Linfeng and Wen, Lijie and Hu, Xuming},
  journal={arXiv preprint arXiv:2411.15268},
  year={2024}
}

@article{cheng2024dreampolish,
  title={DreamPolish: Domain Score Distillation With Progressive Geometry Generation},
  author={Cheng, Yean and Cai, Ziqi and Ding, Ming and Zheng, Wendi and Huang, Shiyu and Dong, Yuxiao and Tang, Jie and Shi, Boxin},
  journal={arXiv preprint arXiv:2411.01602},
  year={2024}
}

@article{hong2024cogvlm2,
  title={CogVLM2: Visual Language Models for Image and Video Understanding},
  author={Hong, Wenyi and Wang, Weihan and Ding, Ming and Yu, Wenmeng and Lv, Qingsong and Wang, Yan and Cheng, Yean and Huang, Shiyu and Ji, Junhui and Xue, Zhao and others},
  journal={arXiv preprint arXiv:2408.16500},
  year={2024}
}

@article{yang2024cogvideox,
  title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
  author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
  journal={arXiv preprint arXiv:2408.06072},
  year={2024}
}

@misc{wang2024lvbench,
      title={LVBench: An Extreme Long Video Understanding Benchmark},
      author={Weihan Wang and Zehai He and Wenyi Hong and Yean Cheng and Xiaohan Zhang and Ji Qi and Shiyu Huang and Bin Xu and Yuxiao Dong and Ming Ding and Jie Tang},
      year={2024},
      eprint={2406.08035},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}