Related papers: CINet: A Learning Based Approach to Incremental Co…

Indoor scene augmentation has become an emerging topic in the field of computer vision and graphics with applications in augmented and virtual reality. However, current state-of-the-art systems using deep neural networks require large…

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…

Learning continuously during all model lifetime is fundamental to deploy machine learning solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with recurrent neural networks could pave the way to a large…

Recent developments in large pre-trained language models have enabled unprecedented performance on a variety of downstream tasks. Achieving best performance with these models often leverages in-context learning, where a model performs a…

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…

In-Context Learning (ICL) is a technique by which language models make predictions based on examples provided in their input context. Previously, their context window size imposed a limit on the number of examples that can be shown, making…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to…

Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We…

Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a…

We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and…

The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…

Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Given pre-segmented videos, the task is to recognize actions…

This work focuses on enhancing the generalization performance of deep reinforcement learning-based robot navigation in unseen environments. We present a novel data augmentation approach called scenario augmentation, which enables robots to…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Real-world objects occur in specific contexts. Such context has been shown to facilitate detection by constraining the locations to search. But can context directly benefit object detection? To do so, context needs to be learned…

We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…

Retrieval-augmented language models have demonstrated performance comparable to much larger models while requiring fewer computational resources. The effectiveness of these models crucially depends on the overlap between query and retrieved…

In-context system identification aims at constructing meta-models to describe classes of systems, differently from traditional approaches that model single systems. This paradigm facilitates the leveraging of knowledge acquired from…

The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…