Come and chat with us in Seoul at ICML!

agentic learning ai lab@agentic-ai-lab.bsky.social · last mo.

Agentic Learning AI Lab @agentic_ai_lab presents at #ICML2026 in Seoul ✈️🇰🇷 Come check out our research 🧵👇

CDS Assistant Professor Mengye Ren (@mengyer.bsky.social) argues in a new paper that AI selfhood requires continual learning. Today’s LLMs wake from amnesia each session and read a diary of a past self — never extending themselves through new experience. nyudatascience.medium.com/to-have-a-se...

To Have a Self, an AI Must Live a Life

Every copy of a large language model begins each conversation identical to every other copy. They share the same weights and the same…

nyudatascience.medium.com

What does it mean to create a new concept rather than retrieve a familiar one? I propose that creativity is what's unfamiliar at first but quickly learnable by an adaptive observer, and show that meta-learning through a frozen Diffusion model produces stylistic & conceptual creations.

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

Improving World Models: A Neuroscience-Inspired Approach to Latent Planning

Humans instinctively map out the physical consequences of their actions before taking them, seamlessly predicting that a dropped glass will…

nyudatascience.medium.com

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!

yingwww.bsky.social@yingwww.bsky.social · 5mo ago

What is a good latent space for world modeling and planning? 🤔 Inspired by the perceptual straightening hypothesis in human vision, we introduce temporal straightening to improve representation learning for latent planning. 📝: agenticlearning.ai/temporal-str...

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...

Politics After AI

From Capital vs. Labor to Acceleration vs. Preservation

mengyeren.substack.com

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

NYU Center for Data Science@nyudatascience.bsky.social · 6mo ago

CDS Asst. Prof. of CS and Data Science Mengye Ren (@mengyer.bsky.social) spoke with The Independent about Moltbook, a social network for AI agents. Ren said the bots primarily repeat language model data rather than demonstrating genuine communication. www.the-independent.com/tech/moltboo...

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!

Chris Hoang@choang.bsky.social · 6mo ago

Animals learn to recognize objects and how they move from observation. SSL on videos emulates “learning by observing” but only for recognition or motion, not both! Our #ICLR2026 work Midway Network is the first to learn both recognition and motion understanding from videos via latent dynamics 🧵

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.

NYU Center for Data Science@nyudatascience.bsky.social · 6mo ago

Do stronger LLMs make better verifiers? Not necessarily when grading themselves. New work led by Courant PhD student @jacklu-me.bsky.social and CDS Asst Prof @mengyer.bsky.social shows that cross-family verification outperforms self-verification. nyudatascience.medium.com/study-reveal...

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.

NYU Center for Data Science@nyudatascience.bsky.social · 8mo ago

Research from CDS Asst Prof @mengyer.bsky.social and Courant PhD student Christopher Hoang shows how the Midway Network learns object recognition and motion jointly from raw video, using motion latents and a gating unit to model real dynamics. nyudatascience.medium.com/watching-the...

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!

NYU Center for Data Science@nyudatascience.bsky.social · 8mo ago

CDS Assistant Professor of Computer Science and Data Science @mengyer.bsky.social and co-author Frank Wu introduce ARQ, a new learning algorithm that skips backpropagation in favor of a more biologically plausible and computationally efficient method. nyudatascience.medium.com/ditching-bac...

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!

Christian Wolf@chriswolfvision.bsky.social · 9mo ago

Midway networks are cool: representation learning of motion and reconstruction jointly. I see similar motivation in V-JEPA 2 "AC", but I really like the execution here: - hierarchical, - backwards features with cross-attention. arxiv.org/abs/2510.05558 C. Hoang, @mengyer.bsky.social NYU

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

eurips.cc

A NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark

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-...

Learning to See Like Animals: How Small Objects in Dense Video Scenes Challenge AI Vision

PooDLe enhances AI vision in real-world videos by improving small object detection.

nyudatascience.medium.com

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...

NeurIPS 2025 Position Paper Track Reviewer Nomination Form

Does this form look suspicious? Report

docs.google.com

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. 🧵