agentic learning ai lab (@agentic_ai_lab) - Twitter Profili

Sabitlenmiş Tweet

agentic learning ai lab@agentic_ai_lab·11 Ara

At Agentic Learning AI Lab, the best part of our research is working with the incredible students. They are the ones writing the code, running the experiments, and solving the hard problems in AI today. As we approach the end of the year, we are fundraising to ensure these students have the resources they need to thrive in 2026. Unlike big industry labs, we rely on grants and gifts to keep our research independent and open. If you’d like to support the next generation of AI researchers of our lab at NYU, please visit the link below!

English

1

9

27

10.6K

agentic learning ai lab retweetledi

Francois Chaubard@FrancoisChauba1·17 Mar

New interview with Dr. Mengye Ren @mengyer (NYU Assistant Professor, and former researcher at Google Brain Toronto working with Prof. Geoffrey Hinton) talking about "shots on goal" to get to AGI. Very interesting takes if you have the time. youtu.be/W5I-B-kxdjo?si…

YouTube

English

2

7

27

8.3K

agentic learning ai lab retweetledi

Mengye Ren@mengyer·17 Mar

It was a real pleasure to speak with @FrancoisChauba1 on his podcast on what the current AI paradigm is missing. Check out our video below --

Francois Chaubard@FrancoisChauba1

New interview with Dr. Mengye Ren @mengyer (NYU Assistant Professor, and former researcher at Google Brain Toronto working with Prof. Geoffrey Hinton) talking about "shots on goal" to get to AGI. Very interesting takes if you have the time. youtu.be/W5I-B-kxdjo?si…

English

0

4

28

8.2K

agentic learning ai lab@agentic_ai_lab·14 Mar

Latent embeddings can be zigzagged and latent planning is hard. In our new research, we found straightening latents lead to better representations. Gradient descent MPC works! We also show why planning is easier theoretically in a linear system! @yingwww_ @ylecun @mengyer

Ying Wang@yingwww_

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-strai…

English

0

1

9

776

agentic learning ai lab retweetledi

NYU Center for Data Science@NYUDataScience·19 Şub

CDS Asst. Prof. of Computer Science and Data Science Mengye Ren (@mengyer) 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. the-independent.com/tech/moltbook-…

English

0

2

5

970

agentic learning ai lab retweetledi

Jack Lu@Jacklu_me·30 Oca

Excited to see my work with @rteehas on "When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers" featured here! arXiv link: arxiv.org/pdf/2512.02304 👀

NYU Center for Data Science@NYUDataScience

Do stronger LLMs make better verifiers? Not necessarily when grading themselves. New work led by Courant PhD student Jack Lu (@Jacklu_me) and CDS Asst Prof Mengye Ren (@mengyer) shows that cross-family verification outperforms self-verification. nyudatascience.medium.com/study-reveals-…

English

0

6

25

3.7K

agentic learning ai lab retweetledi

Chris Hoang@choang333·30 Oca

Our work Midway Network has been accepted to #ICLR2026! Animals learn to recognize objects and how they move just from observing the world. SSL on natural videos emulates “learning by observing” but only tackles recognition or motion, not both! To address this gap, Midway Network is the first SSL architecture to learn both object recognition and motion understanding from natural videos via latent dynamics🧵

English

3

52

401

25.1K

agentic learning ai lab@agentic_ai_lab·20 Ara

arxiv link: arxiv.org/abs/2510.05558

Magyar

0

3

169

agentic learning ai lab@agentic_ai_lab·20 Ara

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

Research from CDS Asst Prof @mengyer and Courant PhD student @choang333 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-w…

English

1

7

570

agentic learning ai lab@agentic_ai_lab·11 Ara

Lab website: agenticlearning.ai Link to donate: bit.ly/48PnznN 100% of your support goes toward student funding and research resources. As a 501(c)(3) institution, your donation is tax-deductible. Help us keep science open!

English

0

2

7

738

agentic learning ai lab@agentic_ai_lab·11 Ara

At Agentic Learning AI Lab, the best part of our research is working with the incredible students. They are the ones writing the code, running the experiments, and solving the hard problems in AI today. As we approach the end of the year, we are fundraising to ensure these students have the resources they need to thrive in 2026. Unlike big industry labs, we rely on grants and gifts to keep our research independent and open. If you’d like to support the next generation of AI researchers of our lab at NYU, please visit the link below!

English

1

9

27

10.6K

agentic learning ai lab@agentic_ai_lab·10 Ara

Excited to share our new research on local RL without using backprop! @mengyer @zequan_wu

NYU Center for Data Science@NYUDataScience

CDS Assistant Professor of Computer Science and Data Science Mengye Ren (@mengyer) 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-backp…

English

0

1

8

1.1K

agentic learning ai lab@agentic_ai_lab·10 Ara

@NYUDataScience @mengyer @zequan_wu

QAM

0

292

NYU Center for Data Science@NYUDataScience·10 Ara

CDS Assistant Professor of Computer Science and Data Science Mengye Ren (@mengyer) 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-backp…

English

1

4

28

14.8K

agentic learning ai lab@agentic_ai_lab·9 Ara

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

English

8

7

92

32.8K

agentic learning ai lab@agentic_ai_lab·6 Ara

Should you use an LLM verifier to help sample solutions at test time? Our new study reveals some key insights. TL;DR: Choose a verifier from a **different** model family than the solver!

Jack Lu@Jacklu_me

Wondering how to get the most out of LLM test-time verification? New study: “When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers". 🔍 37 models, 9 datasets 🔥 Self vs intra-family vs cross-family verification Result: verify across families! 🧵👇

English

0

6

1.3K

agentic learning ai lab@agentic_ai_lab·5 Ara

Context Tuning is a new efficient way to learn new tasks at test time!

Jack Lu@Jacklu_me

ICL is powerful, but only if LLMs actually understand their contexts. Let’s optimize the KV-cache itself for few-shot adaptation! Introducing Context Tuning: 📎 Initialize prefixes from examples ⚙️ Optimize them via gradient descent 🚀 Unlock strong, efficient adaptation 🧵👇

English

0

4

771

agentic learning ai lab retweetledi

Yanlai Yang@YanlaiYang·15 Ağu

Excited to present my work at CoLLAs 2025 @CoLLAs_Conf! In our paper arxiv.org/abs/2501.12254, we tackle the challenge of self-supervised learning from scratch with continuous, unlabeled egocentric video streams, where we propose to use temporal segmentation and a two-tier memory.

English

1

5

34

3.7K

agentic learning ai lab retweetledi

NYU Center for Data Science@NYUDataScience·11 Haz

CDS Asst. Prof. Mengye Ren (@mengyer), Courant PhD students @alexandernwang and Christopher Hoang, and @ylecun introduce PooDLe: a self-supervised learning method enhancing AI vision in real-world videos by improving small object detection. nyudatascience.medium.com/learning-to-se…

English

1

16

69

48.8K

agentic learning ai lab@agentic_ai_lab·20 Nis

Check out our latest paper on representation learning from naturalistic videos →

Mengye Ren@mengyer

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. 🧵

English

0

2

5

1.5K

agentic learning ai lab retweetledi

CoLLAs 2026@CoLLAs_Conf·19 Şub

🚀 Why Lifelong Learning Matters 🚀 Modern ML systems struggle in non-stationary environments, while humans adapt seamlessly. How do we bridge this gap? 📖 Read our latest blog on the vision behind #CoLLAs2025 and the future of lifelong learning research: 🔗 lifelong-ml.cc/blogs/1 #MachineLearning #ContinualLearning #AI #LifelongLearning

English

1

9

23

8K

agentic learning ai lab retweetledi

NYU Center for Data Science@NYUDataScience·22 Oca

New research by CDS MS student Amelia (Hui) Dai, PhD student Ryan Teehan (@rteehas), and Asst. Prof. Mengye Ren (@mengyer) shows that models’ accuracy on current events drops 20% over time—even when given the source articles. Presented at #NeurIPS2024. nyudatascience.medium.com/language-model…

English

0

2

11

5.5K

agentic learning ai lab

Keşfet