In our newest work (led by the amazing
@sunnytqin.bsky.social , w/ @emalach.bsky.social, Samy Jelassi), we investigate a core question for LLMs: "๐ก๐ ๐๐๐๐๐ก๐๐๐๐ ๐๐ ๐๐๐ก ๐ก๐ ๐๐๐๐๐ก๐๐๐๐" in two prototypical logic-heavy puzzles: CountDown and Sudoku.
11.04.2025 16:29 โ ๐ 3 ๐ 2 ๐ฌ 1 ๐ 0
Will be presenting this work at #NeurIPS2024, today 11am, poster #2311. Come visit us!
12.12.2024 16:45 โ ๐ 11 ๐ 1 ๐ฌ 0 ๐ 0
Heading to NeurIPS tomorrow โ๏ธ
Will be presenting a few papers during the week. Ping me if you want to chat!
09.12.2024 14:55 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
I defended my PhD dissertation back in May. I didn't have time to share it widely then (newborn baby), but I think some of you might enjoy it, especially the opening chapters: benjaminedelman.com/assets/disse...
02.12.2024 00:20 โ ๐ 31 ๐ 3 ๐ฌ 3 ๐ 1
Just put together a starter pack for Deep Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list!
go.bsky.app/2qnppia
22.11.2024 21:35 โ ๐ 87 ๐ 31 ๐ฌ 29 ๐ 5
How does test loss change as we change the training data? And how does this interact with scaling laws?
We propose a methodology to approach these questions by showing that we can predict the performance across datasets and losses with simple shifted power law fits.
21.11.2024 15:11 โ ๐ 19 ๐ 7 ๐ฌ 1 ๐ 2
The Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University.
Thinking about how/why AI works/doesn't, and how to make it go well for us.
Currently: AI Agent Security @ US AI Safety Institute
benjaminedelman.com
web: http://maxim.ece.illinois.edu
substack: https://realizable.substack.com
a mediocre combination of a mediocre AI scientist, a mediocre physicist, a mediocre chemist, a mediocre manager and a mediocre professor.
see more at https://kyunghyuncho.me/
Machine Learning Professor
https://cims.nyu.edu/~andrewgw
Machine learning researcher. Professor in ML department at CMU.
work on theoretical foundations of AI, MLLM reliability/Eval, optimization, high dimensional probability/statistics, AI for science/healthcare; director of center on AIF4S @USC ๐ฒ๐๏ธ๐ฅพ๐โโ๏ธ
Associate Professor of Electrical Engineering, EPFL.
Amazon Scholar (AGI Foundations). IEEE Fellow. ELLIS Fellow.
Prof at EPFL
AI โข Climbing
Director of the Center for the Advancement of Progress
Professor at University of Toronto. Research on machine learning, optimization, and statistics.
Foundations of AI. I like simple and minimal examples and creative ideas. I also like thinking about the next token ๐งฎ๐งธ
Google | PhD, CMU |
https://arxiv.org/abs/2504.15266 | https://arxiv.org/abs/2403.06963
vaishnavh.github.io
Research scientist at OpenAI working on reasoning and RL. Previously PhD student at Stanford University working with Percy Liang and Tengyu Ma.
Sr Research Scientist at Google DeepMind, Toronto. Member, Mila. Adjunct, McGill CS. PhD Machine Learning & MASt Applied Math (Cambridge), BSc Math (Warwick). gkdz.org
Postdoc @ EPFL, working on the theory of deep learning. Previously Polytechnique and Sorbonne Universitรฉ.
Applied mathematician working on machine learning, statistics and compilers. Currently doing research at FGV EMAp.
dccsillag.xyz
