We build the MMR: Multi-Modal Reading Benchmark for Evaluating Reading Ability of Large Multimodal Models. The MMR Benchmark paper and code is released and currently available on arXiv.

For some unknown reason, LaTeX occasionally fails to find citations even when they are explicitly listed using \bibitem. This issue can often be resolved by compiling the document twice locally: th...

Here is a customized color map for python plot, I name it “OceanHeart” 🌊💗. The color map is inspried by the animation of a Squirtle holding hearts. Define the color map import matplotlib.pyplot...

I’m switching to electric! I just bought my dream guitar at the Guitar Center San Jose—a stunning Gibson Les Paul in blueberry burst—all thanks to the salary from my Adobe internship!

This is a python script that send email automatically. To use this script, you need to setup an app password for your gmail, following this tutorial. An example: send_email(sender='sender@gmail.co...

This is a simple code that uses stable diffusion XL for text guided image generation. Check the official SDXL huggingface page for more details. A demo image: Generated by: from diffusers imp...

Here is a radar plot function. The python script is available here: radar plot. A demo looks like this: And it could be in dark mode: check for all the available themes: import matplotlib.pypl...

I created a repo, purediffusion. It is also available through pip: pip install purediffusion purediffusion is a torch implementation I used for DDPM with DDIM sampling. This implementation is no...

Our paper LACE, a diffusion model for layout generation is accepted by ICLR 2024 and is currently available on arXiv. Code is will be available at: https://github.com/puar-playground/LACE

This is a short mix of two songs the “happy birthday to you” & “fly me to the moon”. Listen to the MIDI demo: audio The cover ima...