Check out our new work on action abstractions for amortized samplers led by @boussifo.bsky.social! Simple tokenization schemes like BPE result in meaningful action abstractions with several empirical implications for amortized samplers. Come chat with us @iclr-conf.bsky.social!
05.04.2025 01:28 — 👍 5 🔁 0 💬 0 📌 0
Amortizing intractable inference in large language models
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end a...
It's nice to see the elicitation perspective getting discussed! RL on CoT is really just a more reliable way of eliciting latent capabilities of the model than simple prompting. We took this perspective in our work (arxiv.org/abs/2310.04363), which was also one of the first to use RL on CoT.
04.03.2025 02:48 — 👍 2 🔁 0 💬 0 📌 0
Math, Neuroscience, AI. PhD candidate at Mila and University of Montreal; also writes music and dreams of post-growth economies 🧠🪴🇵🇸 Website: https://computationalcognition.ca/author/
PhD student in Physics at UdeM/Mila
Assistant Professor at the Department of Computer Science, University of Liverpool.
https://lutzoe.github.io/
AI Research Scientist || PhD in machine learning || Ensembles, probabilistic machine learning, recurrent neural networks || https://echostatements.github.io
Lead product for Google AI Studio, working on the Gemini API, and AGI, my views!
Assistant Professor @Princeton. Developing robots that plan and learn to help people. Prev: @Cornell, @MIT, @Harvard.
https://tomsilver.github.io/
AI for Science, deep generative models, inverse problems. Professor of AI and deep learning @universitedeliege.bsky.social. Previously @CERN, @nyuniversity. https://glouppe.github.io
Analogue video and audio synthesis. Digital artificial life, intelligence and evolution. Portable experimental music.
AI Architect | North Carolina | AI/ML, IoT, science
WARNING: I talk about kids sometimes
Researcher at Google and CIFAR Fellow, working on the intersection of machine learning and neuroscience in Montréal (academic affiliations: @mcgill.ca and @mila-quebec.bsky.social).
• A PhD in multi-agent reinforcement learning at ETH Zurich
• A chess enthusiast - 2585 Elo @Chesscom)
• Developed the first language model at Google DeepMind capable of playing the game at near super-human level (3200 Elo).
Researcher in machine learning
https://malkin1729.github.io/ / Edinburgh, Scotland / they≥she>he≥0
Mathematician/informatician thinking probabilistically, expecting the same of you.
‘Tis categories in the mind and guns in their hands which keep us enslaved.
causal inference, econometrics, ML, arsenal, loud music, unix, FOSS for scientific computing.
apoorvalal.github.io
(passively) maintains @paperposterbot.bsky.social
PhD student at @cmurobotics.bsky.social working on efficient algorithms for interactive learning (e.g. imitation / RL / RLHF). no model is an island. prefers email. https://gokul.dev/. on the job market!
MSc. @mila-quebec.bsky.social and @mcgill.ca in the LiNC lab
Fixating on multi-agent RL, Neuro-AI and decisions
Ēka ē-akimiht
https://danemalenfant.com/
Research Scientist at Google DeepMind, working on algorithm discovery using AI: AlphaTensor, FunSearch, and beyond
AI for accelerating Scientific Discovery.
PhD student @Mila_Quebec. BEng and MEng/Msc @centralesupelec & @ENS_ParisSaclay
Website: https://jaggbow.github.io/
•PhD student @ https://www.ucl.ac.uk/gatsby 🧠💻
•Masters Theoretical Physics UoM|UCLA🪐
•Intern @zuckermanbrain.bsky.social|
@SapienzaRoma | @CERN | @EPFL
https://linktr.ee/Clementine_Domine
doing a phd in RL/online learning on questions related to exploration and adaptivity
> https://antoine-moulin.github.io/
