I'm a Master's student at Southeast University, School of Computer Science, with a strong background in AI research. My research focuses on multimodal reasoning models, in-context learning, and human-computer interaction systems.
- π I'm currently working as an Algorithm Researcher Intern at Ant Group
- π± I'm exploring multimodal reasoning models such as PRM and Rule-based RL
- π― I'm collaborating with OpenRLHF to develop multimodal RL frameworks
- π« How to reach me: [email protected]
- LMM-R1: A high-performance rule-based RL framework for multimodal models (400+ stars)
- LIVE: Learnable In-Context Vector for Visual Question Answering (NeurIPS 2024)
- Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models (NeurIPS 2024)
- Chat-Based Collaborative Interface: For Personalized Exploratory Tasks (IUI 2025)
- Algorithm Researcher Intern, Ant Group (2024.12 - Present)
- Algorithm Researcher Intern, Microsoft (DKI Group) (2024.07 - 2024.12)
- User Safety Algorithm Engineer Intern, ByteDance (Douyin) (2023.01 - 2023.08)
- AI Engineer Intern, Intel (2022.05 - 2023.01)
- Programming: Python, PyTorch, TensorFlow
- AI/ML: Multimodal Learning, Reinforcement Learning, LLMs, VLMs
- Research Areas: In-Context Learning, Multimodal Reasoning, Human-Computer Interaction
- LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
- Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks (IUI 2025)
- LIVE: Learnable In-Context Vector for Visual Question Answering (NeurIPS 2024)
- Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models (NeurIPS 2024)
- Mimic In-Context Learning for Multimodal Tasks (CVPR 2025)
βοΈ From ForJadeForest