👤 About Me
I completed my B.Eng. at Nankai University and am now an MPhil student at HKUST(GZ) (Red Bird MPhil Program). I previously interned at the Shanghai AI Laboratory, where I worked with Yihao Liu. I am currently a member of LARK Lab, advised by Prof. Zhijiang Guo.
My research interests lie in Agentic AI, LLM Reasoning and MLLMs. I am also broadly interested in agentic RL and its applications in scientific discovery.
If you are interested in my work or would like to chat about research, feel free to drop me an email!
🎓 Education
- The Hong Kong University of Science and Technology (Guangzhou), MPhil Student, starting 2026.08, Guangzhou, China.
- Nankai University, B.Eng. in Computer Science and Technology, 2022.09 - 2026.06, Tianjin, China.
📖 Publications
Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control
Haoze Liu*, Run Liu*, Haiying Xu, et al.
arXiv 2026 · Submitted to AAAI 2027
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Siyu Yan*, Zhuoran Yan*, Haiying Xu*, et al.
arXiv 2026 · Submitted to AAAI 2027
LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning
Haiying Xu*, Zihan Wang*, Song Dai*, Zhengxuan Zhang, Kairan Dou, Xuming Hu
EchoVoices: Preserving Generational Voices and Memories for Seniors and Children
Haiying Xu*, Haoze Liu*, Mingshi Li, Siyu Cai, Guangxuan Zheng, Yuhuang Jia, Jinghua Zhao, Yong Qin
🛠 Skills
- LLM Training: PyTorch, Hugging Face, LoRA, verl, MS-Swift, FlashAttention, PPO, DPO, GRPO.
- Multimodal and Speech Models: CLIP, BLIP-2, LLaVA, Qwen-VL, InternVL, Whisper, VITS, Stable Diffusion.
- RAG and Agents: LangChain, LlamaIndex, FAISS, Milvus, Function Calling, ReAct, Multi-Agent systems.
- Programming: Python, C/C++, Linux, Docker, Git, LaTeX.