Xuyang Liu (刘旭洋)

🌈 I am a third-year Master’s student at Sichuan University . I am also working as a research intern at OPPO Research Institute , supervised by Prof. Lei Zhang (PolyU HK, IEEE Fellow). Previously, I have interned at Ant Group focusing on GUI Agent, and Taobao & Tmall Group working on Efficient VLMs. I’ve also spent half a year visiting MiLAB at Westlake University, supervised by Prof. Donglin Wang. I am fortunate to work closely with Dr. Siteng Huang from DAMO Academy and Prof. Linfeng Zhang from SJTU.

📌 My research interests span Efficient Vision-Language Models, including:

• Efficient Inference: MixKV, V²Drop, VidCom², GlobalCom², FiCoCo, ToCa
• Efficient Training: M2IST, V-PETL Bench, DARA, Sparse-Tuning, AutoGnothi

📢 Recently, I am mainly focusing on Data-centric Model Compression. Feel free to reach out to me via Email liuxuyang@stu.scu.edu.cn, if you are interested in collaborating with me.

🔥 News

• 2025.12.02 🤗🤗 We release STC, a plug-and-play inference acceleration framework for streaming video understanding! Code is available!
• 2025.11.08 🎊🎊 Three papers have been accepted by AAAI 2026, including two LVLM acceleration methods GlobalCom² and FiCoCo, and a RL-based GUI grounding training framework GUI-G²!
• 2025.10.24 🤗🤗 We release MixKV, a plug-and-play framework that enhances existing KV compression methods with consistent performance gains across multiple LVLMs and tasks.
• 2025.08.21 🎊🎊 One first author paper VidCom² about plug-and-play inference acceleration for VideoLLMs has been accepted by EMNLP 2025 main conference! Code is available!
• 2025.05.27 🙌🙌 We release a new paper, pointing to shifting AI efficiency from model-centric to data-centric compression. Project is available! Our paper is honored to be the #2 Paper of the day!
• 2025.03.11 🎊🎊 One first author paper (M2IST) about parameter-, memory-, and time-efficient fine-tuning for referring expression comprehension has been accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)!
• 2025.02.22 🎊🎊 Two papers (ToCa and AutoGnothi) have been accepted by ICLR 2025! Congratulations to all collaborators!
• 2024.09.26 🎊🎊 One co-first author paper (V-PETL) about unified visual parameter-efficient transfer learning benchmark has been accepted by NeurIPS 2024!

📝 Publications

Full publications are on my Google Scholar profile. *: Equal contribution. †: Project leader.

Conference Papers

Xuyang Liu, Ziming Wang, Junjie Chen, Yuhang Han, Yingyao Wang, Jiale Yuan, Jun Song, Linfeng Zhang, Siteng Huang, Honggang Chen, "Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models". In Proceedings of the 40th AAAI Conference on Artificial Intelligence, 2026. [paper] [code]

Yuhang Han^*, Xuyang Liu^*, Zihan Zhang, Pengxiang Ding, Junjie Chen, Donglin Wang, Honggang Chen, Qingsen Yan, Siteng Huang, "Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration". In Proceedings of the 40th AAAI Conference on Artificial Intelligence, 2026. [paper] [page] [code]

Fei Tang, Zhangxuan Gu, Zhengxi Lu, Xuyang Liu, Shuheng Shen, Changhua Meng, Wen Wang, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang, "GUI-G²: Gaussian Reward Modeling for GUI Grounding". In Proceedings of the 40th AAAI Conference on Artificial Intelligence, 2026. [paper] [code] [huggingface paper] [page] [机器之心]

Xuyang Liu^*, Yiyu Wang^*, Junpeng Ma, Linfeng Zhang, "Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models". In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. [paper] [code] [slides] [poster] [Chinese intro]

Chang Zou^*, Xuyang Liu^*, Ting Liu, Siteng Huang, Linfeng Zhang, "Accelerating Diffusion Transformers with Token-wise Feature Caching". In International Conference on Learning Representations (ICLR), 2025. [paper] [page] [code] [量子位] [poster]

Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui Zhang, Xuyang Liu, Weiya Li, Xuming Hu, Linfeng Zhang, "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models". In International Conference on Learning Representations (ICLR), 2025. [paper] [code]

Yi Xin^*, Siqi Luo^*, Xuyang Liu^*, Yuntao Du^*, Haodi Zhou, Xinyu Cheng, Christina Lee, and 10 more authors, "V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark". In Neural Information Processing Systems Datasets and Benchmarks Track (NeurlPS D&B Track), 2024. [paper][page] [code] [poster]

Journal Papers

Xuyang Liu^*, Ting Liu^*, Siteng Huang, Yi Xin, Yue Hu, Quanjun Yin, Donglin Wang, Yuanyuan Wu, Honggang Chen, "M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension". IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025. [paper] [code]

Preprints & Under Submission

Yiyu Wang^*, Xuyang Liu^*,†, Xiyan Gui, Xinying Lin, Boxue Yang, Chenfei Liao, Tailai Chen, Linfeng Zhang, "Accelerating Streaming Video Large Language Models via Hierarchical Token Compression". arXiv preprint arXiv:2512.00891. [paper] [code]

Xuyang Liu^*, Xiyan Gui^*, Yuchao Zhang, Linfeng Zhang, "Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models". arXiv preprint arXiv:2510.20707. [paper] [code]

Junjie Chen^*, Xuyang Liu^*,†, Zichen Wen, Yiyu Wang, Siteng Huang, Honggang Chen, "Variation-aware Vision Token Dropping for Faster Large Vision-Language Models". arXiv preprint arXiv:2509.01552. [paper] [code]

Xuyang Liu^*, Zichen Wen^*, Shaobo Wang^*, Junjie Chen, Zhishan Tao, and 10 more authors, "Shifting AI Efficiency From Model-Centric to Data-Centric Compression". arXiv preprint arXiv:2505.19147. [paper] [project] [huggingface paper] [video]

Ting Liu^*, Xuyang Liu^*, Siteng Huang, Liangtao Shi, Zunnan Xu , Yi Xin, Quanjun Yin, "Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference". arXiv preprint arXiv:2405.14700. [paper] [github]

🤗 Resources

Please find my full repositories on my GitHub profile.

• Awesome Generation Acceleration
  • Duty: Owner.
  • Description: An open-source repository that curates a collection of recent awesome papers on AIGC acceleration.
• Awesome Token-level Model Compression
  • Duty: Owner.
  • Description: An open-source repository that curates a collection of recent awesome papers on token-level model compression.

💻 Experiences

Internships

• Research Intern - OPPO Research Institute, OPPO, Shenzhen
  • Time: Jul 2025 - Present.
  • Thesis: Video Understanding with Large Vision-Language Models.
  • Supervisor: Prof. Lei Zhang.
• Research Intern - Ant Security Lab, Ant Group, Hangzhou
  • Time: Apr 2025 - Jul 2025.
  • Thesis: Multi-modal Graphical User Interface (GUI) Agents.
• Research Intern - Taobao & Tmall Group, Alibaba Group, Beijing
  • Time: Jul 2024 - Mar 2025.
  • Thesis: Efficient Multi-modal Large Language Models.

Visiting

• Research Assistant - EPIC Lab, Shanghai Jiao Tong University, Remote
  • Time: June 2024 - Present.
  • Thesis: Efficient Multi-modal Large Language Models.
  • Supervisor: Prof. Linfeng Zhang.
• Visiting Student - MiLab, Westlake University, Hangzhou
  • Time: Mar 2023 - Sep 2023.
  • Thesis: Efficient Transfer of Vision-language Models.
  • Supervisors: Dr. Siteng Huang and Prof. Donglin Wang.

🎤 Talks

• 2025.06.10: PolyU NLP Group directed by Prof. Wenjie Li: Shifting AI Efficiency From Model-Centric to Data-Centric Compression. [slides]

📠 Services

Conference Reviewer

• International Conference on Learning Representations (ICLR)
• Advances in Neural Information Processing Systems (NeurIPS)
• AAAI Conference on Artificial Intelligence (AAAI)
• ACM International Conference on Multimedia (MM)

Journal Reviewer

• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)