Thang Bui

Senior Lecturer (US equiv Assoc Prof) in Machine Learning @ANUComputing. Previously @Sydney_Uni, @Uber AI and @CambridgeMLG

[Thang Bui @thdbui]

Both papers will be presented on Thursday, 11am - 2pm, posters #605 and #612.

[Thang Bui @thdbui]

At #NeurIPS2025 presenting 2 papers:

Rao-Blackwellised Reparameterisation Gradients with a rising star @kevinhflam, George Deligiannidis, and @yeewhye

Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited with the inimitable Michalis Titsias

[Thang Bui @thdbui]

@timrudner @UofT @VectorInst Congratulations!

[Tim G. J. Rudner @timrudner]

I'm so happy to share that I’ll be joining @UofT as an Assistant Professor of Statistical Sciences and Computer Science, with an appointment at the @VectorInst, in 2026!

I'm recruiting postdocs and PhD students: https://t.co/FWBh0BiDqP!

Please help me spread the word!

🧵(1/5)

[Thang Bui @thdbui]

Indeed! now accepted at TMLR https://t.co/0dFXbReQpf. Also check out Titsias’ concurrent paper.

[Jiaxin Shi @thjashin]

@andrewgwils Still a lot of fun with GP research
https://t.co/iPJxXBccp7
https://t.co/M1PfKMYqkf

[Thang Bui @thdbui]

A similar satellite event for AU/South+ East Asia would be awesome. Shorter travels/cheaper accommodations/potentially increased participation! Happy to chat about it if anyone is keen.

[Kosta Derpanis (sabbatical in Zurich) @CSProfKGD]

Collegues in Europe are running this poll about #NeurIPS2025 participation. If in Europe, highly recommended to participate.

[lexing xie @lexing]

Announcing 2x Research Fellows positions on NLP and machine learning, working w wonderful Jing Jiang, Thang Bui and myself + partners in Data61 - apply by 31 Dec or help spread the words
https://t.co/XQL264Ilv7
more detail in thread

[Julyan Arbel @JulyanArbel]

Thank you @vincefort @markvanderwilk @EmtiyazKhan for organising this great @dagstuhl workshop!
https://t.co/MXYi1gmK2e

[Thang Bui @thdbui]

@pfau Yah not unique to neural nets, for linear models or GP models too, shown in this TMLR paper https://t.co/WKLpPsQzIw

[Thang Bui @thdbui]

Kudos to two rising stars Jack and Charlie! Also check out the 5-min video: https://t.co/uUEhZFfXRv

[Jack Miller @jackm2003]

🚨Paper alert! Grokking Beyond Neural Networks has just been published at TMLR.

https://t.co/EjRx3iFeFT

[Thang Bui @thdbui]

@jackm2003 https://t.co/YMiOJKhvQr

[Tolga Bilge @TolgaBilge_]

Somewhat interesting advertising choice from Anthropic, comparing their newly released Claude 3 to GPT-4 on release (March 2023).

According to Promptbase's benchmarking, GPT-4-turbo scores better than Claude 3 on every benchmark where we can make a direct comparison.

[ioana ciucă @errai34]

Check out this outstanding work from some of the best people I know, fellow @universe_tbd ers and the best co-convenor in the Universe!

Great stuff, @jackm2003 @oneill_c @thdbui. Keep grokking!

[Thang Bui @thdbui]

Grounded explanation of grokking based on the datafit-complexity trade off.

With two fantastic undergrads (!!) @jackm2003 and @oneill_c

More ⬇️

[Jack Miller @jackm2003]

We have recently written a new paper on grokking: https://t.co/6hB29onrkJ. We show that the phenomenon is not limited to neural networks, this motivates a new hypothesis which seeks to explain it.

See the thread below for more details.

@thdbui and @oneill_c.

[Yuan-Sen Ting 丁源森 @TingAstro]

Absolutely thrilled to announce 🚀 AstroLLaMa from @universe_tbd! Introducing our specialized Llama-2 models tailored for astronomers 🌌. This is just the beginning! But our tests already show extraordinary text generation and embeddings for astronomy!💫
https://t.co/fPFI3hGazk

[Josh Nguyen @joshnguyen99]

Happy to announce the release of a new language model, AstroLLaMA. Joint work with the amazing @TingAstro, @errai34 and many amazing collaborators @universe_tbd.

https://t.co/JKMrfV8l27

1/n

[Thang Bui @thdbui]

Fantastic work led by @oneill_c, with @TingAstro @errai34 @robertarail and Jack Miller.

[Yuan-Sen Ting 丁源森 @TingAstro]

📄 Fresh paper out, led by an awesome undergrad 🌟! We dove into a strategy using classifier guidance & negative prompting to spread word tokens, moving them from the 'mundane' zone 🔄. Result? More creativity in hypothesis without losing clarity! 💡

https://t.co/jqI0bOsids

[Thang Bui @thdbui]

Time to name names, it’s @UNSW. If any is thinking about doing postgrad study at UNSW, just don’t!

[Thang Bui @thdbui]

Personal news: I have joined @ANUComputing and my family recently relocated from Sydney to Canberra. Big talking point: my wife has been told her PhD candidature at a university^* in Sydney would be suspended because of this move!

[Thang Bui @thdbui]

^* not disclosing name here as my wife is still discussing next steps with them.

[Yee Whye Teh @yeewhye]

Are you an ML research engineer interested in principled approaches to deep learning and/or Bayesian learning? Are you interested in joining a dynamic, kind and friendly team working on cutting edge research? If so, please apply @DeepMind London office! https://t.co/foV6kEykLs

[Thang Bui @thdbui]

@bipr @ANUComputing Thanks Ben! Awful, indeed. She even managed to get an external ANU supervisor and a desk at ANU but to no avail as the Dean decided that was not enough.

[Thang Bui @thdbui]

I’m hiring multiple PhD students (with full funding) and a two-year postdoc. Get in touch if you are interested!