Inferring 3D human poses from video is highly ill-posed because of depth ambiguity.

Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.

I have updated my course notes on Optimal Transport with a new Chapter 9 on Wasserstein flows. It includes 3 illustrative applications: training a 2-layer MLP, deep transformers, and flow-matching generative models. You can access it here: mathematical-tours.github.io/book-sources...

Hello to all #ICLR reviewers on #MLsky

I wrote a summary of the main ingredients of the neat proof by Hugo Lavenant that diffusion models do not generally define optimal transport. github.com/mathematical...

Perhaps an unpopular opinion, but I don't think the problem with Large Language Model evaluations is the lack of error bars.

Discrete diffusion has become a very hot topic again this year. Dozens of interesting ICLR submissions and some exciting attempts at scaling. Here's a bibliography on the topic from the Kuleshov group (my open office neighbors).

github.com/kuleshov-gro...

Another nano gem from my amazing student
Piotr Nawrot!

A repo & notebook on sparse attention for efficient LLM inference: github.com/PiotrNawrot/...

This will also feature in my #NeurIPS 2024 tutorial "Dynamic Sparsity in ML" with André Martins: dynamic-sparsity.github.io Stay tuned!