Bruno Mlodozeniec
@kayembruno
PhD @Cambridge_Uni | http://brunokm.github.io | Previously @MSFTResearch, @QCOMResearch
Diffusion models are so ubiquitous, but it's difficult to find an introduction that is concise, simple and comprehensive. My supervisor Rich Turner (with me & some other students) has written an introduction to diffusion models that fills this gap: arxiv.org/abs/2402.04384
I used LLMs to generate reviews for my paper after submitting to NeurIPS to prepare for what might come up in the actual reviews. I was pretty naïve thinking this would just be a useful proxy 👀
It's been a busy and exciting first few days at #ICML2025! Huge congratulations to our members on their fantastic presentations so far. Here’s a recap of the work from our group so far. 🧵👇
I will likely be looking for students at the University of Montreal / Mila to start January 2026. The deadline to apply is September 1, 2025. I will share more details later, but wanted to start getting it on people's radar!
I've been seeing a lot of influence functions slander going around lately, but then you check the appendix and see this
This is a huge development. I want to highlight the theoreticians behind the scene, because this paper represents the realization of the impact of years of careful theoretical research. It starts with Greg Yang (@TheGregYang) opening up research on the muP scaling and…
(1/7) @CerebrasSystems Paper drop: arxiv.org/abs/2505.01618 TLDR: We introduce CompleteP, which offers depth-wise hyperparameter (HP) transfer (Left), FLOP savings when training deep models (Middle), and a larger range of compute-efficient width/depth ratios (Right). 🧵 👇
Great to be back from Singapore from #ICLR2025, and super excited to have given my first oral presentation on influence functions for diffusion models!
A reply from a finance firm HFT engineer friend
>be you >work in HFT shaving nanoseconds off latency or extracting bps from models >have existential dread >see this tweet, wonder if your skills could be better used making AGI >apply to attend this party, meet the openai team >build AGI