Runze Tian

Hi there, I am Tian Runze! I am from China CN 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

Nov 07, 2025	Training-Free Method for Parallel Decoding of Autoregressive Models This blog post investigates the possibility of parallel decoding for autoregressive models. The author notes that autoregressive and diffusion models both fundamentally model data probability distributions, and that each has advantages—autoregressive models in training and diffusion models in sampling. The goal is to achieve a training-free way to perform parallel decoding with a pretrained autoregressive model, enabling low-cost accelerated generation.
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).