🧐 Areas of Interest:
- Optimization in Deep Learning
- Multimodal Large Language Models
- Computer Vision
🧑🏻💻 Research Goal: My research goal is to profoundly understand the black-box cornerstone of deep learning by exploring often overlooked and counterintuitive phenomena in foundational models, thereby aiding and witnessing the emergence of new optimization techniques and the evolution of MLLM into a generalist model.
🔍 Current Focus: I have established the Black-Box Optimization & Coupling Bias (BOCB) team with my best research partners & friends. Our team is dedicated to advancing the scientific understanding of black-box optimization problems and the pervasive coupling bias phenomena observed in contemporary artificial intelligence systems, particularly deep neural networks. Through rigorous theoretical analysis and empirical investigation, we aim to call for the community to re-examine research that has been held with high conviction, to uncover the fundamental mechanisms underlying these prevalent challenges in the field of artificial intelligence, and to stimulate the emergence of new optimization technologies.
You can learn more about my recent updates and activities on my personal website at https://tianshijing.github.io.
🌏I warmly welcome the opportunity to collaborate meaningfully, preferably on my research interests or those of the BOCB team. E-mail: [email protected]
Following are some of my favorite repositories that I have contributed to: