research
∙
06/15/2023
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
Current perceptual similarity metrics operate at the level of pixels and...
share
research
∙
06/07/2023
MultiEarth 2023 – Multimodal Learning for Earth and Environment Workshop and Challenge
The Multimodal Learning for Earth and Environment Workshop (MultiEarth 2...
research
∙
06/01/2023
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
We investigate the potential of learning visual representations using sy...
research
∙
05/31/2023
Improving CLIP Training with Language Rewrites
Contrastive Language-Image Pre-training (CLIP) stands as one of the most...
research
∙
05/15/2023
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
This work examines the challenges of training neural networks using vect...
research
∙
04/03/2023
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
In goal-reaching reinforcement learning (RL), the optimal value function...
research
∙
03/23/2023
Persistent Nature: A Generative Model of Unbounded 3D Worlds
Despite increasingly realistic image quality, recent 3D image generative...
research
∙
02/22/2023
Steerable Equivariant Representation Learning
Pre-trained deep image representations are useful for post-training task...
research
∙
12/12/2022
MIRA: Mental Imagery for Robotic Affordances
Humans form mental images of 3D scenes to support counterfactual imagina...
research
∙
11/29/2022
Procedural Image Programs for Representation Learning
Learning image representations using synthetic data allows training neur...
research
∙
11/28/2022
Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
Asymmetrical distance structures (quasimetrics) are ubiquitous in our li...
research
∙
11/23/2022
Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
One of the grand challenges of reinforcement learning is the ability to ...
research
∙
09/26/2022
Totems: Physical Objects for Verifying Visual Integrity
We introduce a new approach to image forensics: placing physical refract...
research
∙
07/14/2022
Developing a Series of AI Challenges for the United States Department of the Air Force
Through a series of federal initiatives and orders, the U.S. Government ...
research
∙
06/30/2022
On the Learning and Learnablity of Quasimetrics
Our world is full of asymmetries. Gravity and wind can make reaching a p...
research
∙
06/30/2022
Denoised MDPs: Learning World Models Better Than the World Itself
The ability to separate signal from noise, and reason with clean abstrac...
research
∙
04/15/2022
MultiEarth 2022 – Multimodal Learning for Earth and Environment Workshop and Challenge
The Multimodal Learning for Earth and Environment Challenge (MultiEarth ...
research
∙
04/14/2022
Any-resolution Training for High-resolution Image Synthesis
Generative models operate at fixed resolution, even though natural image...
research
∙
03/31/2022
Visual Prompting: Modifying Pixel Space to Adapt Pre-trained Models
Prompting has recently become a popular paradigm for adapting language m...
research
∙
03/23/2022
Learning to generate line drawings that convey geometry and semantics
This paper presents an unpaired method for creating line drawings from p...
research
∙
03/03/2022
NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
Thin, reflective objects such as forks and whisks are common in our dail...
research
∙
11/12/2021
Contrastive Feature Loss for Image Prediction
Training supervised image synthesis models requires a critic to compare ...
research
∙
10/28/2021
Learning to Ground Multi-Agent Communication with Autoencoders
Communication requires having a common language, a lingua franca, betwee...
research
∙
10/14/2021
The Neural MMO Platform for Massively Multiagent Research
Neural MMO is a computationally accessible research platform that combin...
research
∙
10/13/2021
OPEn: An Open-ended Physics Environment for Learning Without a Task
Humans have mental models that allow them to plan, experiment, and reaso...
research
∙
07/15/2021
Adaptable Agent Populations via a Generative Model of Policies
In the natural world, life has found innumerable ways to survive and oft...
research
∙
07/01/2021
Learning to See before Learning to Act: Visual Pre-training for Manipulation
Does having visual priors (e.g. the ability to detect objects) facilitat...
research
∙
06/10/2021
Learning to See by Looking at Noise
Current vision systems are trained on huge datasets, and these datasets ...
research
∙
06/09/2021
Generative Models as a Data Source for Multiview Representation Learning
Generative models are now capable of producing highly realistic images t...
research
∙
05/03/2021
Curious Representation Learning for Embodied Intelligence
Self-supervised representation learning has achieved remarkable success ...
research
∙
04/29/2021
Ensembling with Deep Generative Views
Recent generative models can synthesize "views" of artificial images tha...
research
∙
04/27/2021
Explaining in Style: Training a GAN to explain a classifier in StyleSpace
Image classification models can depend on multiple different semantic at...
research
∙
03/18/2021
The Low-Rank Simplicity Bias in Deep Networks
Modern deep neural networks are highly over-parameterized compared to th...
research
∙
03/18/2021
Using latent space regression to analyze and leverage compositionality in GANs
In recent years, Generative Adversarial Networks have become ubiquitous ...
research
∙
12/10/2020
iNeRF: Inverting Neural Radiance Fields for Pose Estimation
We present iNeRF, a framework that performs pose estimation by "invertin...
research
∙
08/24/2020
What makes fake images detectable? Understanding properties that generalize
The quality of image generation and manipulation is reaching impressive ...
research
∙
07/27/2020
Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
Humans integrate multiple sensory modalities (e.g. visual and audio) to ...
research
∙
05/20/2020
What makes for good views for contrastive learning
Contrastive learning between multiple views of the data has recently ach...
research
∙
05/20/2020
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Contrastive representation learning has been outstandingly successful in...
research
∙
03/25/2020
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
The focus of recent meta-learning research has been on the development o...
research
∙
01/31/2020
Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networks
Progress in multiagent intelligence research is fundamentally limited by...
research
∙
11/12/2019
Experience-Embedded Visual Foresight
Visual foresight gives an agent a window into the future, which it can u...
research
∙
10/23/2019
Contrastive Representation Distillation
Often we wish to transfer representational knowledge from one neural net...
research
∙
10/01/2019
Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
Pushing is a fundamental robotic skill. Existing work has shown how to e...
research
∙
07/16/2019
On the "steerability" of generative adversarial networks
An open secret in contemporary machine learning is that many models work...
research
∙
06/24/2019
GANalyze: Toward Visual Definitions of Cognitive Image Properties
We introduce a framework that uses Generative Adversarial Networks (GANs...
research
∙
06/13/2019
Contrastive Multiview Coding
Humans view the world through many sensory channels, e.g., the long-wave...
research
∙
03/02/2019
Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
The emergence of complex life on Earth is often attributed to the arms r...
research
∙
02/14/2019
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Contemporary sensorimotor learning approaches typically start with an ex...
research
∙
12/01/2018