Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Deep Learning architectures usually aren't trained to perform search at test time, leading to sample inefficiency + poor generalization. Latent Program Network (LPN) builds in test-time adaption by learning a latent space that can be searched. Clem Bonnet matt

Ndea

10,789 subscribers

30,803 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

DeCAF won the #ICML Test of Time Award 2024! Big congrats to trevordarrell (my PhD advisor at MIT), and Jeff Donahue. 🎉 You may not heard of DeCAF, but it is everywhere! DeCAF stands for Deep Convolutional Activation Features. Published ten years ago, the DeCAF paper is a groundbreaking work that shows the activation features of the last few layers of a deep network contain useful features that can be "repurposed" for or "transferred to" many other tasks, not just the original task the network was trained for. I created this exercise to show where we can see DeCAF's influence in some of the most well-known architectures: AlexNet, ViT, U-Net, CLIP, and Latent Diffusion, to prove that DeCAF's "Test of Time Award" is well-deserved! Let's give a round of applause to DeCAF, the unsung hero of computer vision.

DeCAF won the #ICML Test of Time Award 2024! Big congrats to trevordarrell (my PhD advisor at MIT), and Jeff Donahue. 🎉 You may not heard of DeCAF, but it is everywhere! DeCAF stands for Deep Convolutional Activation Features. Published ten years ago, the DeCAF paper is a groundbreaking work that shows the activation features of the last few layers of a deep network contain useful features that can be "repurposed" for or "transferred to" many other tasks, not just the original task the network was trained for. I created this exercise to show where we can see DeCAF's influence in some of the most well-known architectures: AlexNet, ViT, U-Net, CLIP, and Latent Diffusion, to prove that DeCAF's "Test of Time Award" is well-deserved! Let's give a round of applause to DeCAF, the unsung hero of computer vision.

Tom Yeh

21,420 views • 1 year ago

Been dying for this to arrive! 🤯 Limited edition. You can only find it in the latent space.

Been dying for this to arrive! 🤯 Limited edition. You can only find it in the latent space.

Javi Lopez ⛩️

87,978 views • 1 year ago

ICML 2026: Latent Reasoning in TRMs is Secretly a Policy Improvement Operator Why does recursive reasoning, especially latent reasoning, actually work? The theory is still young, and even mechanistic explanations are limited. We close part of this gap by showing that latent reasoning is secretly doing policy improvement. Each recursion pushes the model steadily toward the target. Based on this view, we propose an algorithm that boosts learning and inference efficiency by up to 18x.

ICML 2026: Latent Reasoning in TRMs is Secretly a Policy Improvement Operator Why does recursive reasoning, especially latent reasoning, actually work? The theory is still young, and even mechanistic explanations are limited. We close part of this gap by showing that latent reasoning is secretly doing policy improvement. Each recursion pushes the model steadily toward the target. Based on this view, we propose an algorithm that boosts learning and inference efficiency by up to 18x.

Arip

23,733 views • 3 days ago

The latent space of earlier generative models like GANS can linearly encode concepts of the data. What if the data was model weights? We present weights2weights, a subspace in diffusion weights that behaves as an interpretable latent space over customized diffusion models.

The latent space of earlier generative models like GANS can linearly encode concepts of the data. What if the data was model weights? We present weights2weights, a subspace in diffusion weights that behaves as an interpretable latent space over customized diffusion models.

Amil Dravid

94,262 views • 2 years ago

Learn how to combine a deep learning model for pose estimation to perform a 3D reconstruction using two cameras 📸

Learn how to combine a deep learning model for pose estimation to perform a 3D reconstruction using two cameras 📸

MATLAB

15,665 views • 1 year ago

Is it possible to adapt a neural network on the fly at the test time to cope with distribution shifts? RNA does precisely that by creating a closed-loop feedback system. We will present it on Wed afternoon at #ICCV2025. 1/n

Is it possible to adapt a neural network on the fly at the test time to cope with distribution shifts? RNA does precisely that by creating a closed-loop feedback system. We will present it on Wed afternoon at #ICCV2025. 1/n

Amir Zamir

21,685 views • 2 years ago

Apple Learning Coach is a free professional learning program that trains instructional coaches, digital learning specialists, and other coaching educators to help teachers effectively use Apple technology in the classroom. Apply today.

Apple Learning Coach is a free professional learning program that trains instructional coaches, digital learning specialists, and other coaching educators to help teachers effectively use Apple technology in the classroom. Apply today.

Apple Education

25,869 views • 3 years ago

1. Machine Learning Specialization Break into AI with this 3-course program by Andrew Ng. What you’ll learn: → Build machine learning models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

1. Machine Learning Specialization Break into AI with this 3-course program by Andrew Ng. What you’ll learn: → Build machine learning models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

Amit

55,462 views • 6 months ago

POV: you agree to test a non slip bonnet

POV: you agree to test a non slip bonnet

MNJ

133,087 views • 1 year ago

u js trained on test bro, it's not that deep

u js trained on test bro, it's not that deep

llm_enjoyer

197,030 views • 21 days ago

CS projects in 2015: Snake game in Python that took you 2 weeks to make. CS projects in 2030: Deep Learning Snake Game Neural Network.

CS projects in 2015: Snake game in Python that took you 2 weeks to make. CS projects in 2030: Deep Learning Snake Game Neural Network.

ₕₐₘₚₜₒₙ

132,224 views • 2 years ago

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

Ricardo Martin-Brualla

21,685 views • 1 year ago

We’re all looking at the latent space, but ⁦gray ❄️🫧⁩ is inside of it.

We’re all looking at the latent space, but ⁦gray ❄️🫧⁩ is inside of it.

Max

11,388 views • 1 year ago

One week left to apply! ⏰ Apple Learning Coach is a free professional learning program that trains instructional coaches, digital learning specialists, and other educators to help teachers get more out of Apple technology.

One week left to apply! ⏰ Apple Learning Coach is a free professional learning program that trains instructional coaches, digital learning specialists, and other educators to help teachers get more out of Apple technology.

Apple Education

27,059 views • 3 years ago

1. Machine Learning Specialization. Break Into AI with this 3-course program by Andrew Ng. What You’ll learn: → Build ML models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

1. Machine Learning Specialization. Break Into AI with this 3-course program by Andrew Ng. What You’ll learn: → Build ML models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

Abhishek

364,242 views • 1 year ago

At Nodepay, we’ve built a living ecosystem fueled by unused bandwidth, real-time data retrieval, user-owned AI innovation, & rewards that flow back to the contributors. Picture a global AI network constantly learning and evolving—all powered by our community. How it works: 🧵

At Nodepay, we’ve built a living ecosystem fueled by unused bandwidth, real-time data retrieval, user-owned AI innovation, & rewards that flow back to the contributors. Picture a global AI network constantly learning and evolving—all powered by our community. How it works: 🧵

Nodepay

964,975 views • 1 year ago

Corey DeAngelis recommending the Federal Gov require the Classic Learning Test as a sane alternative to the SAT and ACT duopoly

Corey DeAngelis recommending the Federal Gov require the Classic Learning Test as a sane alternative to the SAT and ACT duopoly

Jeremy Wayne Tate

27,669 views • 8 months ago

1/ What if you could earn rewards just by learning about crypto? GREED Academy is back with Semester 2, with over 120k in prizes for those who lock, learn, and test their knowledge onchain. Eight weeks. Five sponsors. Big incentives. Time to lock in 📕

1/ What if you could earn rewards just by learning about crypto? GREED Academy is back with Semester 2, with over 120k in prizes for those who lock, learn, and test their knowledge onchain. Eight weeks. Five sponsors. Big incentives. Time to lock in 📕

GREED Academy 📕

39,360 views • 1 year ago

It's your turn to build an empire that stands the Test of Time. To celebrate the free, game-changing Test of Time update, get 40% off #Civ7 on Steam!

It's your turn to build an empire that stands the Test of Time. To celebrate the free, game-changing Test of Time update, get 40% off #Civ7 on Steam!

Sid Meier's Civilization VII

18,157 views • 29 days ago