research
∙
07/24/2023
On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
Pre-training has been widely adopted in deep learning to improve model p...
share
research
∙
07/11/2023
Objaverse-XL: A Universe of 10M+ 3D Objects
Natural language processing and 2D vision models have attained remarkabl...
research
∙
06/16/2023
Neural Priming for Sample-Efficient Adaptation
We propose Neural Priming, a technique for adapting large pretrained mod...
research
∙
05/31/2023
Bytes Are All You Need: Transformers Operating Directly On File Bytes
Modern deep learning approaches usually transform inputs into a modality...
research
∙
05/30/2023
AdANNS: A Framework for Adaptive Semantic Search
Web-scale search systems learn an encoder to embed a given query which i...
research
∙
04/27/2023
DataComp: In search of the next generation of multimodal datasets
Large multimodal datasets have been instrumental in recent breakthroughs...
research
∙
04/25/2023
Stable and low-precision training for large-scale vision-language models
We introduce new methods for 1) accelerating and 2) stabilizing training...
research
∙
04/24/2023
Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
A common assumption when training embodied agents is that the impact of ...
research
∙
03/15/2023
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
We propose Dataset Reinforcement, a strategy to improve a dataset once s...
research
∙
03/08/2023
FastFill: Efficient Compatible Model Update
In many retrieval systems the original high dimensional data (e.g., imag...
research
∙
01/10/2023
Neural Radiance Field Codebooks
Compositional representations of the world are a promising step towards ...
research
∙
12/20/2022
RangeAugment: Efficient Online Augmentation with Range Learning
State-of-the-art automatic augmentation methods (e.g., AutoAugment and R...
research
∙
12/15/2022
Objaverse: A Universe of Annotated 3D Objects
Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebIm...
research
∙
12/09/2022
Object Goal Navigation with End-to-End Self-Supervision
A household robot should be able to navigate to target locations without...
research
∙
12/08/2022
Phone2Proc: Bringing Robust Robots Into Our Chaotic World
Training embodied agents in simulation has become mainstream for the emb...
research
∙
12/08/2022
Editing Models with Task Arithmetic
Changing how pre-trained models behave – e.g., improving their performan...
research
∙
10/19/2022
lo-fi: distributed fine-tuning without communication
When fine-tuning large neural networks, it is common to use multiple nod...
research
∙
09/27/2022
Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents
The perception system in personalized mobile agents requires developing ...
research
∙
09/23/2022
Safe Real-World Reinforcement Learning for Mobile Agent Obstacle Avoidance
Collision avoidance is key for mobile robots and agents to operate safel...
research
∙
09/07/2022
What does a platypus look like? Generating customized prompts for zero-shot image classification
Open vocabulary models are a promising new paradigm for image classifica...
research
∙
08/10/2022
Patching open-vocabulary models by interpolating weights
Open-vocabulary models like CLIP achieve high accuracy across many image...
research
∙
07/27/2022
Break and Make: Interactive Structural Understanding Using LEGO Bricks
Visual understanding of geometric structures with complex spatial relati...
research
∙
06/14/2022
ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
Massive datasets and high-capacity models have driven many recent advanc...
research
∙
05/26/2022
Matryoshka Representations for Adaptive Deployment
Learned representations are a central component in modern ML systems, se...
research
∙
03/15/2022
Object Manipulation via Visual Target Localization
Object manipulation is a critical skill required for Embodied AI agents ...
research
∙
03/10/2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
The conventional recipe for maximizing model accuracy is to (1) train mu...
research
∙
01/02/2022
The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents
The last few years have witnessed substantial progress in the field of e...
research
∙
12/06/2021
Forward Compatible Training for Representation Learning
In visual retrieval systems, updating the embedding model requires recom...
research
∙
12/01/2021
Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text
Communicating with humans is challenging for AIs because it requires a s...
research
∙
10/08/2021
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
When deploying deep learning models to a device, it is traditionally ass...
research
∙
09/04/2021
Robust fine-tuning of zero-shot models
Large pre-trained models such as CLIP offer consistent accuracy across a...
research
∙
07/07/2021
LanguageRefer: Spatial-Language Model for 3D Visual Grounding
To realize robots that can understand human instructions and perform mea...
research
∙
06/04/2021
MERLOT: Multimodal Neural Script Knowledge Models
As humans, we understand events in the visual world contextually, perfor...
research
∙
06/02/2021
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
Learning binary representations of instances and classes is a classical ...
research
∙
06/01/2021
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World
We propose PIGLeT: a model that learns physical commonsense knowledge th...
research
∙
04/28/2021
Pushing it out of the Way: Interactive Visual Navigation
We have observed significant progress in visual navigation for embodied ...
research
∙
02/20/2021
Learning Neural Network Subspaces
Recent observations have advanced our understanding of the neural networ...
research
∙
11/18/2020
Layer-Wise Data-Free CNN Compression
We present an efficient method for compressing a trained neural network ...
research
∙
10/16/2020
What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
Learning effective representations of visual data that generalize to a v...
research
∙
07/09/2020
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
Autonomous agents must learn to collaborate. It is not scalable to devel...
research
∙
07/06/2020
In the Wild: From ML Models to Pragmatic ML Systems
Enabling robust intelligence in the wild entails learning systems that o...
research
∙
06/26/2020
Supermasks in Superposition
We present the Supermasks in Superposition (SupSup) model, capable of se...
research
∙
05/01/2020
Probing Text Models for Common Ground with Visual Representations
Vision, as a central component of human perception, plays a fundamental ...
research
∙
04/22/2020
Visual Commonsense Graphs: Reasoning about the Dynamic Context of a Still Image
Even from a single frame of a still image, people can reason about the d...
research
∙
04/14/2020
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
Visual recognition ecosystems (e.g. ImageNet, Pascal, COCO) have undenia...
research
∙
04/07/2020
Evaluating Machines by their Real-World Language Use
There is a fundamental gap between how humans understand and use languag...
research
∙
03/26/2020
Grounded Situation Recognition
We introduce Grounded Situation Recognition (GSR), a task that requires ...
research
∙
03/18/2020
Watching the World Go By: Representation Learning from Unlabeled Videos
Recent single image unsupervised representation learning techniques show...
research
∙
02/15/2020
Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
Fine-tuning pretrained contextual word embedding models to supervised do...
research
∙
02/08/2020