Zhenyuan Chen

Blog

Welcome to my blog! Here I share my thoughts and insights on AI, computer vision, and remote sensing.

Recent Posts

📮 Subscribe to my blog: RSS Feed (Use with Feedly, NewsBlur, or any RSS reader)

Advanced Representation Learning in Remote Sensing Image

December 29, 2025

A comprehensive study of advanced techniques for remote sensing representation learning, including latest self-supervised learning and fine-tuning for downstream tasks.


Exploring Machine Learning in Perspective of Manifold Learning

December 17, 2025

An exploration of machine learning through four key questions, analyzing deep neural networks, generalizability, inversion problems, and the bitter lesson from the perspective of manifold learning.


Reproducibility in Diffusers

December 17, 2025

How to control randomness and ensure reproducibility in Diffusers pipelines.


Show Your Talents: Interactive Research Profile Visualization

December 04, 2025 Repository

An interactive radial bar chart to visualize research interests and skills, inspired by academic profile metrics. Built with HTML and Plotly.js, it offers a customizable and engaging way to showcase expertise.


From U-Nets to DiTs: The Architectural Evolution of Text-to-Image Diffusion Models (2021–2025)

November 09, 2025

A comprehensive analysis of how diffusion model architectures evolved from U-Net backbones to Diffusion Transformers, transforming text-to-image generation capabilities. Covers the complete evolution from Stable Diffusion through the latest models like Qwen-Image and SANA 1.5, with interactive timelines and architectural comparisons.


Geoffrey Hinton’s 2024 Nobel Prize Lecture: Hopfield Networks and Boltzmann Machines

December 07, 2024 Video

Full transcript of Geoffrey Hinton’s Nobel Prize in Physics lecture explaining Hopfield networks, Boltzmann machines, and their role in the deep learning revolution. A remarkable explanation of complex technical concepts without using equations.


Diffusion Model Track: Methods and Application in Image Synthesis

November 17, 2024 PDF

An overview of diffusion models for image synthesis, with a focus on pioneering work from OpenAI, including GLIDE, DALL-E 2, and Consistency Models.


Introducing Latex-Slides-Template-GenAI: A Modern LaTeX Beamer Template

October 11, 2025 Repository

A comprehensive LaTeX Beamer template with modern design, advanced citation management, and professional styling. Perfect for academic presentations and keynotes, featuring per-slide references, multi-page PDF support, and clean aesthetics.


World Models: Background, Applications and Opportunities

October 10, 2025 PDF

An exploration of world models in AI, covering video generation, representation learning, and the Platonic representation hypothesis. This post discusses recent advances in models like CogVideoX and their applications in image editing and world simulation.


More posts coming soon...

← Back to Home


Powered by Jekyll and Minimal Light theme.