AI agents often struggle to plan movements because their internal representations of the physical world can be overly tangled. CDS PhD student Ying Wang shows how straightening these pathways improves AI navigation. Accepted to ICML 2026. nyudatascience.medium.com/improving-wo... 1/2

Agentic Learning AI Lab is at #ICLR2026, come check out our work! @mengyer.bsky.social @choang.bsky.social @jacklu-me.bsky.social Frank Wu🧵

New preprint: The Self Requires Learning. Self-consciousness requires continual learning + world-modeling. I introduce "bounded integration" to connect perspective, identity, and self-representation — and diagnose what current AI systems have and lack. Full paper: mengyeren.com/research/202...

Project proposals this year by CDS Faculty Fellow Mateo Dulce Rubio, CDS Assoc. Prof. Carlos Fernandez-Grande, Asst. Prof. Grace Lindsay (@neurograce.bsky.social), and Asst. Prof. Mengye Ren (@mengyer.bsky.social)!

Latent trajectories from pretrained models are curved and zigzagged. We add a simple straightening objective that makes the latent transitions smooth and trajectories straightened. Check out our latest research by @yingwww.bsky.social @yann-lecun.bsky.social and colleagues!

AI may be reshaping not just the economy, but the political assumptions built around labor. In this blog post, I explore what this could mean for the future landscape of political economy: mengyeren.substack.com/p/politics-a...

Sharing my thoughts on Moltbook in a recent interview by The Independent.

I have updated my tutorial on making Vision Language Action models. This tutorial starts with a basic Transformer and walks people through the steps to transform it into a full VLA that uses PaliGemma as the pretrained VLM. Links below.

Corporate PRs are becoming a disservice to science. We see amazing things with no idea how they were done. It's just a way to grab smart people and pump equity, while discouraging junior students by making them think there's nothing left to be done in research.

Check out our Midway Network paper on learning hierarchical latent motion tokens from watching videos. Recently got accepted to ICLR 2026!

Verifiers are increasingly being used today in RL to provide rewards. We did a systematic study on when it is the best to use LLMs to verify solutions.

Our latest research Midway Networks learn recognition and motion representations from scratch by letting the network learn from watching videos. The latent motion vectors are refined in a top-down hierarchy. Interesting tracking results using our forward perturbation viz.

We are so comfortable with the concept of pretraining in foundation models today that we assume an AI is supposed to have seen everything humanity has created. 1/2

Excited to share our new research on local RL without backprop!

Lab gathering at #NeurIPS2025. Proud of this year’s work and excited about the ideas we’re building toward next!

I will be at NeurIPS next week. Let's connect if you are also interested in continual learning AI!

Be part of #NeurIPS2025 in Mexico City! Submit your proposals: 📅 Deadlines Tutorials: Sept 26 👉 neurips.cc/Conferences/... Workshops: Sept 30 👉 neurips.cc/Conferences/... Socials: Oct 1 👉 neurips.cc/Conferences/... Startup Pitch: Oct 15 👉 neurips.cc/Conferences/...

Pitch your AI startup at NeurIPS 2025 in Mexico City! The application deadline is just a month away on October 15th. Learn more and apply now: neurips.cc/Conferences/...

Watch this new video of work by CDS Asst. Prof. Mengye Ren (@mengyer.bsky.social) and colleagues, who built PooDLe, an algorithm that helps AI systems learn from complex environments like busy streets. The method mimics how humans process cluttered scenes. www.nyu.edu/about/news-p...

We're excited to announce a second physical location for NeurIPS 2025, in Mexico City, which we hope will address concerns around skyrocketing attendance and difficulties in travel visas that some attendees have experienced in previous years. Read more in our blog: blog.neurips.cc/2025/07/16/n...

NeurIPS is endorsing EurIPS, an independently-organized meeting which will offer researchers an opportunity to additionally present NeurIPS work in Europe concurrently with NeurIPS. Read more in our blog post and on the EurIPS website: blog.neurips.cc/2025/07/16/n... eurips.cc

NeurIPS is seeking additional ethics reviewers this year. If you are able and willing to participate in the review process, please sign up at the form in the link: neurips.cc/Conferences/... Please share this call with your colleagues!

CDS Asst. Prof. @mengyer.bsky.social, Courant PhD students Alex N. Wang and Christopher Hoang, and @ylecun.bsky.social introduce PooDLe: a self-supervised learning method enhancing AI vision in real-world videos by improving small object detection. nyudatascience.medium.com/learning-to-...

The NeurIPS Position Track is seeking additional reviewers this year. If you'd like to serve or nominate a colleague, please complete our nomination form! docs.google.com/forms/d/e/1F...

The proposed 5% remittance tax on non-citizens is another blatant attack on foreign workers, who've contributed tremendously to the U.S. economy, have little path to citizenship, no birthright for their kids, and will face double taxation on their hard-earned dollars.

How can we leverage naturalistic videos for visual SSL? Naturalistic, i.e. uncurated, videos are abundant and can emulate the egocentric perspective. Our paper at ICLR 2025, PooDLe🐩, proposes a new SSL method to address the challenges of learning from naturalistic videos. 🧵

A single man's decision wiped out 20% of the global wealth and still going...

America will become a T-shirt manufacturing superpower!

Love that stock market crashing...

"A French scientist was denied entry to the US after immigration officers at an airport searched his phone and found messages in which he had expressed criticism of the Trump administration." --- So much for freedom of speech.

Not that I am personally affected by the new rules, but desk rejection on reciprocal reviews of every author is not a proportional penalty on junior students and can burden junior PIs who submit papers to wider venues. Plus it hurts the community by throwing away valid reviews.

www.wsj.com/arts-culture... wow i didn’t know about it

The tiny industry research "awards" that ultimately waste thousands of hours of PIs' time that would otherwise be more useful... What a predatory job on getting a preview of all of the cutting-edge ideas for free.

CDS is hiring a Clinical Professor of Data Science. Teach ML, programming, and specialized courses in our 60 5th Ave building. Renewable contracts with promotion opportunities. Apply by April 1, 2025. For details, see: apply.interfolio.com/155349 #MachineLearning #ML #AIjobs

My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12

This is a moment to celebrate for the long standing foundational contributions to RL by Sutton and Barto Congrats to them and all their collaborators over the years who made this long line of advancements possible www.acm.org/media-center...

Shockingly accurate. Waiting for a grant to be approved before starting the research project is #toolittletolate.

The oval office is a disgrace of humanity.

English as the official language of the greatest country of America? Weak. Should rename the language to “American”.

Keir Starmer said that Canada is a "divide" between the US and UK that doesn't exist, and he wouldn't comment on it because the UK and US are so close. He caved like a coward.

The UN is now a joke.

We live in a time where the sovereignty of a nation can be joked around by a bully and no one is able to stand up to it.

Leavitt now sounds like a news broadcaster from North Korea.

Any regime that puts up a banned word list is revealing its own weaknesses.

Almost all grant-review meetings under Trump 2.0 remain suspended at the US National Institutes of Health (NIH), preventing the world’s largest public funder of biomedical research from spending much of its US$47 billion annual budget. https://go.nature.com/4gM6oW4

It's not implausible that a number of countries will join the nuke club in the next decade.

At the current pace of development, allowing American tech companies to continue to dominate the market of the Western allied countries imposes significant national security threats.

There is little incentive for a self-interested, nationalistic government to fund open research, because open means sharing with the globe. And once open science collapses, it doesn’t come back. The system will permanently shifts toward closed, secretive, military-driven or profit-driven research.

Perhaps this country does not need research. What if everyone stops publishing for a year?