agentic learning ai lab
@agentic-ai-lab.bsky.social
AI research lab @nyu.edu led by Mengye Ren @mengyer.bsky.social | Partially run by students | agenticlearning.ai
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🧵
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...
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 @mengyer.bsky.social and colleagues!
yingwww.bsky.social@yingwww.bsky.social · 5mo agoWhat 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...
Sharing my thoughts on Moltbook in a recent interview by The Independent.
NYU Center for Data Science@nyudatascience.bsky.social · 6mo agoCDS 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...
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. Check out the blog post below to learn more.
NYU Center for Data Science@nyudatascience.bsky.social · 6mo agoDo 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...
Babies learn to perceive the world and develop object and motion recognition in the early stages of life. Can a network bootstrap this understanding just by watching video? Check out the new blog post featuring our latest research on the Midway Network.
NYU Center for Data Science@nyudatascience.bsky.social · 8mo agoResearch 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...
Excited to share our new research on local RL without backprop!
NYU Center for Data Science@nyudatascience.bsky.social · 8mo agoCDS 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!
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
Check out our latest paper on representation learning from naturalistic videos →
Mengye Ren@mengyer.bsky.social · last yr.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. 🧵
New research by CDS MS student Amelia (Hui) Dai, PhD student Ryan Teehan, and Asst. Prof. Mengye Ren (@mengyer.bsky.social) shows that models’ accuracy on current events drops 20% over time—even when given the source articles. Presented at #NeurIPS2024. nyudatascience.medium.com/language-mod...
Language Models’ Prediction of Current Events Degrades Over Time, Even With Latest Information
Language models lose accuracy on predicting events over time, even with access to up-to-date information.
nyudatascience.medium.com