Search Results for author:
Found 24 papers, 12 papers with code
SODA: Bottleneck Diffusion Models for Representation Learning
We introduce SODA, a self-supervised diffusion model, designed for representation learning.
Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
We introduce a challenging decision-making task that we call active acquisition for multimodal temporal data (A2MT).
Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods
Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training.
Extended Intelligence
We argue that intelligence, construed as the disposition to perform tasks successfully, is a property of systems composed of agents and their contexts.
Transframer: Arbitrary Frame Prediction with Generative Models
We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction.
Object discovery and representation networks
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks.
HiP: Hierarchical Perceiver
This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.
General-purpose, long-context autoregressive modeling with Perceiver AR
Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression.
Ranked #35 on
Language Modelling
on WikiText-103
SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
Using SyMetric, we identify a set of architectural choices that significantly improve the performance of a previously proposed model for inferring latent dynamics from pixels, the Hamiltonian Generative Network (HGN).
Which priors matter? Benchmarking models for learning latent dynamics
Learning dynamics is at the heart of many important applications of machine learning (ML), such as robotics and autonomous driving.
Perceiver IO: A General Architecture for Structured Inputs & Outputs
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015
(Average End-Point Error metric)
Imitation by Predicting Observations
Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior.
Perceiver: General Perception with Iterative Attention
The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models.
Ranked #29 on
Audio Classification
on AudioSet
Game Plan: What AI can do for Football, and What Football can do for AI
The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball, basketball, and tennis.
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
We explore whether integrated tasks like Mujoban can be solved by composing RL modules together in a sense-plan-act hierarchy, where modules have well-defined roles similarly to classic robot architectures.
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
To encourage progress towards this goal we introduce a set of physically embedded planning problems and make them publicly available.
Hamiltonian Generative Networks
The Hamiltonian formalism plays a central role in classical and quantum physics.
Keyframing the Future: Discovering Temporal Hierarchy with Keyframe-Inpainter Prediction
To flexibly and efficiently reason about temporal sequences, abstract representations that compactly represent the important information in the sequence are needed.
Codes, Functions, and Causes: A Critique of Brette's Conceptual Analysis of Coding
Here, we argue that Brette's conceptual analysis mischaracterizes the structure of causal claims in coding and other forms of analysis-by-decomposition.
Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning
We propose a model that learns to discover these important events and the times when they occur and uses them to represent the full sequence.
Learning what you can do before doing anything
We introduce a loss term that encourages the network to capture the composability of visual sequences and show that it leads to representations that disentangle the structure of actions.
Predicting the Future with Transformational States
We couple this latent state with a recurrent neural network (RNN) core that predicts future frames by transforming past states into future states by applying the accumulated state transformation with a learned operator.
Understanding image motion with group representations
Our results demonstrate that this representation is useful for learning motion in the general setting where explicit labels are difficult to obtain.
Fast, Robust, Continuous Monocular Egomotion Computation
We propose robust methods for estimating camera egomotion in noisy, real-world monocular image sequences in the general case of unknown observer rotation and translation with two views and a small baseline.
