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
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)
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.
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
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.
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!
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.
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
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
📄 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
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!
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
@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.