Gatsby Computational Neuroscience Unit
@GatsbyUCL
Followers
6K
Following
473
Media
30
Statuses
608
We study mathematical principles of learning, perception & action in brains & machines. Funded by Gatsby Charitable Foundation. Also on bluesky & mastodon.
London, United Kingdom
Joined September 2019
🎊 Congratulations to Kevin Huang (@KevinHanHuang1) on passing his PhD viva with minor corrections! 🥳. 🔖 Universality beyond the classical asymptotic regime
6
1
104
RT @Aaditya6284: Excited to present this work in Vancouver at #ICML2025 today 😀 Come by to hear about why in-context learning emerges and….
0
5
0
RT @ArthurGretton: Distributional diffusion models with scoring rules at #icml25 . Fewer, larger denoising steps using distributional losse….
0
59
0
RT @ArthurGretton: Accelerated Diffusion Models via Speculative Sampling, at #icml25 !. at 16:30 Tuesday July 15 poster E-3012. https://t.c….
0
46
0
RT @zhexwang: (1/6) Can Autoregressive Models (ARMs) go beyond fixed or random generation orders and learn the optimal order to generate ne….
0
8
0
Leena Chennuru Vankadara will also give: . - a tutorial 'Training Neural Networks at Any Scale' (Mon 14 Jul); . - and a talk at WiML Symposium at ICML (Wed 16 Jul). Don't miss out!.
0
0
5
👋 Attending #ICML2025 next week? Don't forget to check out work involving our researchers!
1
5
29
RT @SWC_Neuro: It was a pleasure to welcome work experience students to SWC and @GatsbyUCL this week through the Camden STEAM initiative wi….
0
1
0
RT @ClementineDomi6: Excited to share our ICML Oral paper on learning dynamics in linear RNNs!🎉🎉.
0
3
0
🥳 Congratulations to Clementine Domine on passing her PhD viva with minor corrections! 🎉. 🔖 Balancing Learning Regimes: The Impact of Prior Knowledge on the Dynamics of Neural Representations
10
9
383
RT @StatMEPapers: Dimitri Meunier, Antoine Moulin, Jakub Wornbard, Vladimir R. Kostic, Arthur Gretton. [. Demystify….
0
3
0
RT @SWC_Neuro: New research shows long-term learning is shaped by dopamine signals that act as partial reward prediction errors. The study….
0
3
0
RT @KevinHanHuang1: Last but not least of my travel updates: Courtesy of the very kind @Chau9991, I'm giving a talk at 14:30, 27 Jun @NTU_c….
0
1
0
RT @KevinHanHuang1: Meanwhile, excited to be in #Lyon for #COLT2025, with a co-first author paper ( with the amazin….
0
7
0
RT @KevinHanHuang1: Missing ICML due to visa :'(, but looking forward to share our ICML paper ( as a poster at #Bay….
0
6
0
RT @ArthurGretton: Composite Goodness-of-fit Tests with Kernels, now out in JMLR!. Test if your distribution comes….
0
5
0
RT @Aaditya6284: Excited to share this work has been accepted as an Oral at #icml2025 -- looking forward to seeing everyone in Vancouver, a….
0
5
0
RT @SaxeLab: How does in-context learning emerge in attention models during gradient descent training? . Sharing our new Spotlight paper @….
0
22
0