Search Results for author:
Found 23 papers, 7 papers with code
ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
Deep learning is providing a wealth of new approaches to the old problem of novel view synthesis, from Neural Radiance Field (NeRF) based approaches to end-to-end style architectures.
Improved Compositional Generalization by Generating Demonstrations for Meta-Learning
Choosing good supports from the training data for a given test query is already a difficult problem, but in some cases solving this may not even be enough.
Hierarchical Imitation Learning with Vector Quantized Models
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively.
Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning
Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment.
Learning Explicit Object-Centric Representations with Vision Transformers
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressive for the task of object segmentation in images.
Continuous Monte Carlo Graph Search
To address this problem, we propose Continuous Monte Carlo Graph Search (CMCGS), an extension of MCTS to online planning in environments with continuous state and action spaces.
Compositional Generalization in Grounded Language Learning via Induced Model Sparsity
We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems.
Improved Training of Physics-Informed Neural Networks with Model Ensembles
Learning the solution of partial differential equations (PDEs) with a neural network is an attractive alternative to traditional solvers due to its elegance, greater flexibility and the ease of incorporating observed data.
Learning Trajectories of Hamiltonian Systems with Neural Networks
A popular approach is to use Hamiltonian neural networks (HNNs) which rely on the assumptions that a conservative system is described with Hamilton's equations of motion.
A Grid-Structured Model of Tubular Reactors
We propose a grid-like computational model of tubular reactors.
A Relational Model for One-Shot Classification
We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation.
Learning to Assist Agents by Observing Them
On the other hand, offline data about the behavior of the assisted agent might be available, but is non-trivial to take advantage of by methods such as offline reinforcement learning.
Behaviour-conditioned policies for cooperative reinforcement learning tasks
We suggest a method, where we synthetically produce populations of agents with different behavioural patterns together with ground truth data of their behaviour, and use this data for training a meta-learner.
Automating Privilege Escalation with Deep Reinforcement Learning
AI-based defensive solutions are necessary to defend networks and information assets against intelligent automated attacks.
SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models
Despite the proven effectiveness of Transformer neural networks across multiple domains, their performance with Electronic Health Records (EHR) can be nuanced.
Learning of feature points without additional supervision improves reinforcement learning from images
In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene.
Learning to Play Imperfect-Information Games by Imitating an Oracle Planner
We experimentally show that planning with naive Monte Carlo tree search does not perform very well in large combinatorial action spaces.
Regularizing Model-Based Planning with Energy-Based Models
Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data.
Regularizing Trajectory Optimization with Denoising Autoencoders
Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning.
Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples.
Recurrent Ladder Networks
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models.
Linear State-Space Model with Time-Varying Dynamics
The time dependency is obtained by forming the state dynamics matrix as a time-varying linear combination of a set of matrices.
Variational Gaussian-process factor analysis for modeling spatio-temporal data
We present a probabilistic latent factor model which can be used for studying spatio-temporal datasets.
