Runze Tian
Undergraduate Student @ School of Statistics, Renmin University of China; Intern @ GenSI Lab, THU-AIR
Hi there, I am Tian Runze! I come from China and I am passionate about Mathematics and AI Technologies. I am an individual who enjoys experimenting, thinking, learning, and creating.
I am currently a graduate student in the elite statistics program at the School of Statistics, Renmin University of China. I am also a research intern at GenSI Lab, THU-AIR, where I work on cutting-edge generative AI research.
Through this personal website, I document my research journey and share learning notes, hoping to record my growth in the academic world and exchange ideas with like-minded researchers.
My research focuses on Generative Models with applications in natural language processing and computational biology.
- 💬 Diffusion Language Models: Exploring diffusion-based approaches for text generation, understanding, and controllable generation
- 🧬 Molecular Generation: Developing generative models for small molecule design and drug discovery
- 🧪 Protein Generation: Advancing protein structure generation and protein design using deep learning
news
| Nov 03, 2025 | I set up my personal Page! |
|---|
latest posts
| Feb 01, 2026 | Masking Schedulers of Mask Diffusion Model In Mask Diffusion Models (MDM), the Noise Scheduler is pivotal for learning capacity and sampling quality. This paper presents a unified analysis addressing three core challenges —— Exposure Bias induced by Absorb mechanisms, efficiency bottlenecks from Intrinsic Order, and joint probability deviations from Independence Assumptions. We systematically review mainstream strategies, comparing their efficacy in semantic capture, remasking, and efficiency to elucidate how refined scheduling reshapes token dependencies. Finally, we outline future directions for overcoming these underlying logical defects. |
|---|---|
| Nov 05, 2025 | Flow Matching and Continuous Normalizing Flows This post explores Flow-based Models, Continuous Normalizing Flows (CNFs), and Flow Matching (FM). We discuss Normalizing Flows, derive the conditional flow matching objective, and examine special instances including diffusion models and optimal transport. |
| Nov 03, 2025 | The Unification of DDPM and Score-based Models This post explores the unification of DDPM and Score-based Models in diffusion generative modeling. We show how x-prediction and score-prediction are fundamentally equivalent, and how both can be viewed through the lens of Stochastic Differential Equations (SDEs). |