Канал: Andrew Melnik

Describe, Explain, Plan and Select [part 2]

Describe, Explain, Plan and Select [part 2]

Shape complexity estimation using VAE

Shape complexity estimation using VAE

Instruct AI to pay all of us

Instruct AI to pay all of us

Rerender

Rerender

Emad Mostaque - Stability.ai

Emad Mostaque - Stability.ai

Describe, Explain, Plan and Select [part 1]

Describe, Explain, Plan and Select [part 1]

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

Tracking Everything Everywhere All at Once

Tracking Everything Everywhere All at Once

BERT (language model). How to train BERT?

BERT (language model). How to train BERT?

ChatGPT simply put how does it work?

ChatGPT simply put how does it work?

Voyager: An Open-Ended Embodied Agent with Large Language Models

Voyager: An Open-Ended Embodied Agent with Large Language Models

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

Riffusion - Stable diffusion for real-time music generation

Riffusion - Stable diffusion for real-time music generation

CLIP Interrogator [explained] What a good prompt might be to create new images like an existing one?

CLIP Interrogator [explained] What a good prompt might be to create new images like an existing one?

MineCLIP: Foundation Model for MineDojo (Minecraft). #mineclip #minedojo #minecraft

MineCLIP: Foundation Model for MineDojo (Minecraft). #mineclip #minedojo #minecraft

#minerl #vpt Learning to play Minecraft with Video PreTraining (VPT) - Part 2

#minerl #vpt Learning to play Minecraft with Video PreTraining (VPT) - Part 2

#Shorts DINOv2: State-of-the-art computer vision models with self-supervised learning

#Shorts DINOv2: State-of-the-art computer vision models with self-supervised learning

CLIP: Connecting text and images

CLIP: Connecting text and images

#minerl #vpt Learning to play Minecraft with Video PreTraining (VPT) - Part 1

#minerl #vpt Learning to play Minecraft with Video PreTraining (VPT) - Part 1

AI representation of God - Jordan Peterson

AI representation of God - Jordan Peterson

Editing Face Images with StyleGAN

Editing Face Images with StyleGAN

ReLMoGen [Explained] Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

ReLMoGen [Explained] Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

The ultimate use of AI

The ultimate use of AI

Driving among Flatmobiles [explained]

Driving among Flatmobiles [explained]

MyStyle: A Personalized Generative Prior [Explained]

MyStyle: A Personalized Generative Prior [Explained]

StyleGAN3 [Explained]: Alias-Free Generative Adversarial Networks

StyleGAN3 [Explained]: Alias-Free Generative Adversarial Networks

(GPEN) GAN Prior Embedded Network for Blind Face Restoration in the Wild

(GPEN) GAN Prior Embedded Network for Blind Face Restoration in the Wild

Long Horizon Visual Planning with Goal Conditioned Hierarchical Predictors

Long Horizon Visual Planning with Goal Conditioned Hierarchical Predictors

Differentiable Physics and Stable Modes for Tool Use and Manipulation Planning

Differentiable Physics and Stable Modes for Tool Use and Manipulation Planning

Critic Guided Segmentation of Rewarding Objects in First-Person Views

Critic Guided Segmentation of Rewarding Objects in First-Person Views

Solving Physics Puzzles by Reasoning about Paths (NeurIPS 2020) - PHYRE

Solving Physics Puzzles by Reasoning about Paths (NeurIPS 2020) - PHYRE

Semi-Parametric Topological Memory for Navigation (SPTM)

Semi-Parametric Topological Memory for Navigation (SPTM)

Deep Q-Network & Dueling network architectures for deep reinforcement learning

Deep Q-Network & Dueling network architectures for deep reinforcement learning