James Requeima
@jamesrequeima
Followers
349
Following
95
Media
2
Statuses
36
Postdoctoral fellow at the University of Toronto/Vector Institute. Former PhD student in Machine Learning at the University of Cambridge CBL lab.
Joined July 2011
@DavidDuvenaud and I have a new microscope to look at the beliefs LLMs have about all sorts of quantities. What should we point it at?.
LLMs have complex joint beliefs about all sorts of quantities. And my postdoc @jamesrequeima visualized them! In this thread we show LLM predictive distributions conditioned on data and free-form text. LLMs pick up on all kinds of subtle and unusual structure: 🧵
0
0
10
RT @VectorInst: 🌡️ Breakthrough: Canadian AI revolutionizes weather forecasting. Vector postdoc @jamesrequeima co-developed Aardvark Weathe….
0
2
0
RT @arjunashok37: Context is Key🗝️ is accepted at ICML 2025! 📈 . Let's catch up if you'll be at ICML 🛬. See the poster and tweet thread bel….
0
10
0
RT @timrudner: .@jamesrequeima gave the third invited talk of the day at #AABI2025! . **LLM Processes**
0
1
0
RT @dhir_anish: Understanding causes is key to science. Finite observational data alone isn't enough. While Bayes offers a framework to de….
0
30
0
Happy to have been a part of the great team that produced this report!.
Food prices in Canada likely to increase by 3 to 5% next year: Canada's Food Price Report 2025
0
0
1
RT @arjunashok37: (New paper alert!). Forecasting models typically rely on numerical historical data. However, in many cases, numerical dat….
0
31
0
RT @ikwess: Really excited about this! We've put effort into making the model accessible with code that fits in a Tweet. 😊. pip install mic….
0
7
0
RT @tom_r_andersson: 📢 Excited to announce 'Environmental sensor placement with convolutional Gaussian neural processes', out now in @EnvDa….
0
16
0
RT @tom_r_andersson: Where should we measure the environment to minimise uncertainty about weather and climate? 🎲⛅. I'm excited to share th….
0
8
0
RT @tom_r_andersson: QUIZ: One of these plots shows temperature around Antarctica. The others are samples from a model conditioned on obs a….
0
3
0
RT @ikwess: Happy to announce our #ICLR2023 paper Autoregressive Conditional Neural Processes!. w/ @stratosmarkou, @jamesrequeima, @AndrewF….
0
12
0
RT @shakir_za: Great presentation from @tom_r_andersson on day 2 @Climformatics 🎉 Active learning improve how we understand the Antarctic.….
0
8
0
RT @ikwess: I'm very excited to announce the release of Plum 2.0!. With this release, Plum is fully powered by Beartype, which means that P….
0
4
0
RT @DavidDuvenaud: I should have announced this before, but a year ago I switched my research focus to AI existential risk reduction and go….
0
113
0
RT @tom_r_andersson: 📢Thrilled to be presenting 'Environmental Sensor Placement with Convolutional Gaussian Neural Processes' at a #NeurIPS….
0
7
0
RT @latentjasper: @ylecun Yes ok, but why do they have to shout so much while they're learning?.
0
8
0
RT @ikwess: Still using latent variables to get correlations out of your Neural Process?. Then consider Gaussian Neural Processes (GNP)!. ✓….
0
32
0
RT @CambridgeEllis: Did you miss our second @Cambridge_Uni ELLIS Unit seminar in @Cambridge_Eng with Prof. Richard Turner, a leading resear….
0
5
0
RT @siddharthswar: Ever wondered why variational inference + natural gradients + neural networks might be a good idea? Are you curious to f….
0
43
0
RT @ikwess: @CambridgeMLG is launching a blog, featuring a first two-part post about what keeps a Bayesian awake at night by Richard E. Tur….
0
36
0