The first rule of sharing arXiv links

🚀 The new call for Principal Investigators at the ELLIS Institute Tübingen is now open! We are looking for Principal Investigators as Hector Endowed Fellows in all areas of Machine Learning, Artificial Intelligence, and related fields. These positions offer the exciting

Check out RepTok, which represents each image as a single continuous latent token, and leverages pre-trained SSL encoders for highly efficient generative model training. This work was led by our excellent LMU collaborators with a couple of us from Apple research!

🚀 Come work with me in the Machine Learning Research team at Apple! I’m looking for FT research scientists with a strong track of impactful publications on generative modeling (NeurIPS, ICML, ICLR, CVPR, ICCV, etc.) to join my team and work on fundamental generative modeling

My hot take: I hate all the PyTorch community's distribution strategy names (FooParallel). It's not even about parallelism!! All names should just be "shard X along Y" and that's it. Fully self explanatory and never ambiguous.

any resemblance to real events is purely coincidental

Come intern at Ai2! we are looking for PhD researchers who want to advance the science of language models… you get to drive major parts of next Olmo models, and publish your work!

Missed our workshop at ICCV? Or want to revisit your favorite talk? 🎤 All keynote slides are now uploaded! 👉 musi-workshop.github.io

Even from NeurIPS experiments a decade ago, the bottom 25% of papers had a 5% chance of acceptance whereas the top 25% had a 50% chance. Review scores are noisy! With the recent flood of papers and the downfall of reviews, the correlation between merit and acceptance is going to

Most people assume you need a massive dataset to distill flow models. We challenge that. Is data actually necessary? Or perhaps it is a liability? Introducing FreeFlow: We achieve SOTA (1.49 FID on ImageNet-512) 1-step image generation without a single data sample. 🧵👇[1/n]

Lots of pixel space diffusion papers are doing the rounds this week, many of them seemingly rediscovering the benefits of the multiscale structure of UNets in the Transformer era🤭 Personally, I think we'll be doing latent diffusion for a while longer. The computational

So much discourse either fully embraces or rejects whatever is the current thing in AI. But the truth can be more subtle: The current thing is awful. The current thing is the best thing so far. The current thing will keep getting better. The future thing can be much better.

I’m confident the PCs + Board didn't make their decision lightly, and they have access to much more information than the public does. Rash reactions don't solve anything; we need to be patient. Advice I received more than a decade ago that I find apt now: - What you say today,

🔥 Excited to announce our NeurIPS 2025 Spotlight paper: DisMo – Disentangled Motion Representations for Open-World Motion Transfer! ⏳ TL;DR: We learn abstract, semantic motion and attach it to new content for open-world motion transfer. 👇Thread👇

📢 Another #NeurIPS, another diffusion circle! Join us to talk about diffusion models on Friday Dec 5 at 3:30PM in San Diego! Bayside terrace outside room 11 (upstairs) ☀️🚢🌊 Please help spread the word, tell your friends! No slides, no talks, we just sit down and chat 🗣️

Wondering how to attend an ML conference the right way? ahead of NeurIPS 2025 (30k attendees!) here are ten pro tips: 1. Your main goals: (i) meet people (ii) regain excitement about work (iii) learn things – in that order. 2. Make a list of papers you like