About Me
Hello! I am a second-year Master’s student at Jianghan University.
My research interests mainly include multimodal understanding and generation, multimodal large language models, and natural language processing.
I am always open to academic discussions and welcome opportunities for research collaborations. Please feel free to reach out to me via email.
News
- 💼 [05/2026]: Left HiThink Research.
- 🚀 [04/2026]: One paper has been accepted to ICMR 2026 (CCF-B), First Author. 《CodeMNER: Vision-Language Models are Better Multimodal Named Entity Recognizers via Progressive Vision-Code Alignment》. [Paper]
- 🚀 [04/2026]: One paper has been accepted to ICMR 2026 (CCF-B), Second Author. 《Query-Guided Conflict Inference and Incongruity-Aware Alignment for Implicit Hate Speech Detection in Videos》. [Paper]
- 💼 [10/2025]: Joined HiThink Research as a Research Intern.
- 🏆 [08/2025]: One paper has been accepted to PRICAI 2025 (CCF-C), First Author. 《AMCCL: Adaptive Multi-scale Convolution Fusion Network with Contrastive Learning for Multimodal Sentiment Analysis》. [Paper]
- 🌱 [01/2025]: Started my AI research journey.
Education
- Master
Computer Technology | Jianghan University | 2024 - 2027 - Bachelor
Electronic and Information Engineering | Jianghan University | 2020 - 2024
Intern
- Research Intern, HiThink Research, 2025.10 - 2026.05
- Multimodal Document Image Editing: Developed edit pipeline, constructed benchmarks, and developed complex agentic image edit workflow.
- Factual Hallucination Detection: Developed a three-stage Agent system comprising atomic fact segmentation, information retrieval (Web & Financial databases), and reasoning/judgment.
- Algorithm Intern, MEIZU, 2025.09 - 2025.10
- Mobile GUI Agent: Applied reinforcement learning for GUI Agent development on mobile operating systems.
Research Interests
- Multimodal Understanding and Generation
- Natural Language Processing
- Multimodal Large Language Models and Agents
