Search Results for author:
Found 9 papers, 4 papers with code
Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs).
Improving fine-grained understanding in image-text pre-training
We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs.
Ensembles and Encoders for Task-Free Continual Learning
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each presented only once).
Encoders and Ensembles for Task-Free Continual Learning
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once).
Continual Reinforcement Learning with Multi-Timescale Replay
In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent.
An Explicitly Relational Neural Network Architecture
With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data.
Policy Consolidation for Continual Reinforcement Learning
We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments.
Continual Reinforcement Learning with Complex Synapses
Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of previously acquired knowledge.
Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
We highlight the advantage of our approach in one of the hardest games -- Montezuma's revenge -- for which the ability to handle sparse rewards is key.
