Hao-Xuan Ma   马浩轩

Biography

I am presently pursuing my graduate studies at LAMDA@Nanjing University, advised by Prof. Hanjia Ye.

I currently focus on Model Reuse and Agentic RL, with additional interests in leveraging LLMs for recommendation systems and quantitative trading.

Selected Publications

* denotes equal contribution. ♦ denotes project leader.

MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing Haoxuan Ma*, Guannan Lai*, Han-Jia Ye arXiv preprint, 2026 [Paper] [Code]

Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment Ruoxi Cheng*, Haoxuan Ma*, Weixin Wang*, Ranjie Duan, Xiaojun Jia International Conference on Learning Representations (ICLR), 2026 [Paper]

Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models Xu Yang, Yingzhe Peng, Haoxuan Ma, Shuo Xu, Chi Zhang, Yucheng Han, Hanwang Zhang Neural Information Processing Systems (NeurIPS), 2024 [Paper] [Code]

Experience

• Aug.2023 - Jan.2024, LLM Post-Training Intern, Huawei
• Jul.2024 - Jan.2025, LLM Research Intern, Shanghai AI Laboratory

Awards

• 2^nd place at The 3rd Perception Test Challenge, Hour-long QA Track. (ICCV 2025 Workshop)
• Silver Medal at Google Research - Identify Contrails to Reduce Global Warming. (Kaggle Competition)
• Bronze Medal at CAFA 5 Protein Function Prediction. (Kaggle Competition)
• Outstanding Undergraduate Thesis Award 2025.
• President Scholarship 2024.

Misc

• Hero of the Alliance in World of Warcraft, 2023