Jack Yang

Lecturer in Material Science and Engineering @UNSW and @MMFI_UNSW Computational chemists. Working on ML-driven material discoveries. Views are my own.

[Jack Yang @jackyang_csp]

For the past few months, I've been studying the basics of diffusion generative model, for which Jianlin Su has written a series of blogs in Chinese, which I found much easier to understand the logics behind. So I've decided to translate it, and here are the first 11 blogs.

[Jack Yang @jackyang_csp]

@OUtside2014 just the same as how you would do it for the 2nd order. interface it with phono3py. havent tried it, but it should work.

[Jack Yang @jackyang_csp]

https://t.co/37lCgBZQut
New preprint alert! We had a closer look at modelling lattice dynamics with the MACE foundation models.

[Jack Yang @jackyang_csp]

Oh shit, my molecular dynamic simulation has successfully discovered Australia!

[Jack Yang @jackyang_csp]

Should have been to library more often.

[Jack Yang @jackyang_csp]

@TimothyDuignan Just had a try on MACE foundation model, interesting results although not something unexpected. Materials that are more stable mechanicallly did show better performance compared to those that are not stable. Will do more analyses and probably write a small paper on it:-)

[Jack Yang @jackyang_csp]

@cryptopatrick @Jianlin_S I'm glad that someone else also found it useful, not just me killing my time. :-)
Unfortunately it's a cold wetty winter down here in Australia. 😪

[Jack Yang @jackyang_csp]

For the past few months, I've been studying the basics of diffusion generative model, for which Jianlin Su has written a series of blogs in Chinese, which I found much easier to understand the logics behind. So I've decided to translate it, and here are the first 11 blogs.

[Jack Yang @jackyang_csp]

@Jianlin_S Thank you for writing these inspiring blogs. I learned a lot, even though I cannot say I fully understand them!

[Jack Yang @jackyang_csp]

@cryptopatrick I dont think there is of any problem. pinning the original author here:@Jianlin_S

[Jack Yang @jackyang_csp]

@ChengBingqing Just saw your post. This is very interesting as I have collaborators who works a lot in ferroelectrics, it opens up lots of possibilities with MLP.

[Jack Yang @jackyang_csp]

@joaquinbarroso I have the book on the left, never understood a single page

[Corin Wagen @CorinWagen]

In scientific computation, there's a large cultural divide between physics- and ML-based approaches.

My latest blog post argues that physics–ML hybrids will be the future, despite offending both fields. (ft. spicy quotes from @pranamanam + some wisdom from @manntis4)

[Jack Yang @jackyang_csp]

After spending last couple of months reading on diffusion generative models for materials discoveries, I'm wondering are we being taken over by the mathematicians? Surely the maths & models are cool & hard, but I failed to get much inspiration in materials science perspective.😅

[Jack Yang @jackyang_csp]

I think, if I am correct, generative AI for crystal generation is a bit of an overkill, a simple mathematical optimisation under constrains may work well enough, as shown here.

[Jack Yang @jackyang_csp]

The endpoint of materials science is mathematics.

[Jack Yang @jackyang_csp]

github: https://t.co/o5x6bVwNtd

[Jack Yang @jackyang_csp]

This recent work is out now @PCCP :
https://t.co/M64Go8ZsPW

[Jack Yang @jackyang_csp]

Wrapping up the year with a preprint on @ChemRxiv https://t.co/xyIaSBUIAd, a piece of work started pre-covid and finally ready to see the world.

[Jack Yang @jackyang_csp]

Utterly not impressed with the reviewer from @PCCP, after two rounds of reviews and for the first time, I am considering withdrawing my submission from the journal. I rather just leave it on @ChemRxiv.

[Microsoft Research @MSFTResearch]

Microsoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. https://t.co/z9yOaV7VGo