Confessions of a researchaholic

January 23, 2023

Asian competitive advantage for SIGGRAPH

Filed under: Real — liyiwei @ 10:30 am
Tags: ,

I liked to joke that Asian folks have a competitive advantage for SIGGRAPH since its deadline is usually before the lunar new year, but this year proves a rare exception.

Neither matters that much to me anymore, though.

January 3, 2023

2050 is as close as 1996

Filed under: Real — liyiwei @ 6:28 pm

When I started my PhD study around 1996 I felt that I have some basic intuition about the different fields of computer science. Nobody understands everything, but at least I felt that if I want I can dive into any particular subject when the need arises.

Now, I am overwhelmed by what is happening inside graphics and HCI, my main focus, not to mention other fields, in particular ML and vision.

With this (hyper?) exponential rate of knowledge growth, I cannot even imagine what would happen in 2050. (I have nightmares about this several times already.)
I doubt any individual human brain can handle these without some biological or computational assistance.

Below is ChatGPT’s response to the above:

It’s understandable to feel overwhelmed by the rapid pace of knowledge growth in the field of computer science. It can be difficult to keep up with all the developments and advances, especially in specific areas like graphics, HCI, ML, and vision.

One way to deal with this is to focus on staying up-to-date in your own area of expertise, while also being aware of developments in other related fields. It may not be possible or necessary to be an expert in everything, but having a broad understanding of what’s happening in the field can be valuable.

Another approach is to make use of tools and resources that can help you stay informed and keep track of new developments. This might include subscribing to relevant newsletters, following key researchers and organizations on social media, and using search engines and databases to find the latest research and information.

Finally, it’s important to remember that it’s okay to not know everything. No one person can possibly keep up with everything that’s happening in the field, and it’s important to recognize and accept the limits of your own knowledge. Instead of trying to know everything, focus on staying curious and continuing to learn and grow as a professional.

December 25, 2022

Frame-by-frame handdrawn FX

Filed under: Real — liyiwei @ 7:32 pm
Tags: ,

I belatedly completed this course on hand-drawn secondary dynamic effects, such as smoke, fire, and fluid.
The exercises were quite time-consuming, which I finally found the time to work on during my sabbatical + holiday break.
While automation would certainly be beneficial, it remains an open research question on how to autocomplete the varied effects that are covered in the course.

November 25, 2022

Ketchup splattering

Filed under: Real — liyiwei @ 11:15 am
Tags: ,

I can totally see some fluid simulation folks publishing an upcoming SIGGRAPH paper about ketchup splattering.

November 16, 2022

Why you should write your own paper, at least the first draft

Filed under: Real — liyiwei @ 10:38 am
Tags: ,

Writing is an important skill for not only publishing and communication but also other career tasks. If you cannot do it for whatever reason (language, habit, psychology, etc.) it is better to learn as soon as possible.

Nobody else knows your ideas and thoughts better than yourself. Writing by someone else is not very likely to accurately reflect what you have in mind.

If you find it difficult to express your thoughts, it can be a sign that the thinking is not clear enough and writing can help refine it.

Do whatever to come up with a first draft. Do not worry about nitty gritty details like grammar as long as your collaborators can understand what you are trying to say. We can iterate the paper draft together to improve the not only the writing but also our thinking and execution of the project.

November 11, 2022

Watching presentation videos in faster speed

Filed under: Real — liyiwei @ 5:40 pm
Tags: ,

Sometimes I watch presentation videos in double speed to save time and heighten focus (more attention is needed to parse narrations playing in faster speed).

November 8, 2022

Deep focus

Filed under: Real — liyiwei @ 10:54 am
Tags: , ,

Recently I realized that I have not spent enough time for deep thinking and I can notice that my ideas started to suffer. Some of the causes were self-inflicted, such as letting myself distracted by meetings, slacks, or emails.

Regaining self-control is in order.

October 2, 2022

The little cookie girl with dall-e paintings

Filed under: Imaginary — liyiwei @ 10:56 am
Tags: ,

This is an experiment to generate images directly from texts from the little cookie girl.
Each prompt below is appended with “oil painting by Rembrandt”.

On a freezing New Year’s Eve, a happy young girl, warm and well clothed, huddles in the alley between two houses, trying to sell cookies, which she eats one by one, to keep herself occupied.

In the sweetness of the cookies she sees a series of comforting visions: the warm iron stove, the lovely roast goose, the great glorious Christmas tree. Each vision disappears as a cookie was eaten.

In munching the next cookie she sees her grandmother, the only person that also made cookies with her. To keep the vision of her grandmother alive as long as possible, the girl consumes the entire pack of cookies.

When the cookies are gone the girl is full to the throat, and she takes Uber to carry her home.

The next morning, the father finds the girl sleeping on her bed with a smile on her face, and expresses joy. He does not know about the wonderful visions she had seen, or how happy she is with all the cookies in her belly.

September 9, 2022

img2img stable diffusion

Filed under: Imaginary,Real — liyiwei @ 5:32 pm
Tags: , ,

I experimented with stable diffusion over some of my own manual drawings and here are the results.

Next Page »

Theme: Rubric. Get a free blog at