Related papers: Exploiting generalization in the subspaces for fas…

Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory…

Large Language Models (LLMs) exhibit a troubling duality, capable of both remarkable generalization and brittle, verbatim memorization of their training data. This unpredictability undermines their reliability in high-stakes applications.…

Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of…

Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstream tasks of interest. However, different downstream tasks…

In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional…

In this paper, we consider a transfer reinforcement learning problem involving agents with different action spaces. Specifically, for any new unseen task, the goal is to use a successful demonstration of this task by an expert agent in its…

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

Diffusion models have gained prominence in generating high-quality sequences of text. Nevertheless, current approaches predominantly represent discrete text within a continuous diffusion space, which incurs substantial computational…

Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language…

We challenge a fundamental assumption of diffusion models, namely, that a large number of latent-states or time-steps is required for training so that the reverse generative process is close to a Gaussian. We first show that with careful…

We are motivated by the problem of learning policies for robotic systems with rich sensory inputs (e.g., vision) in a manner that allows us to guarantee generalization to environments unseen during training. We provide a framework for…

Model-based reinforcement learning methods typically learn models for high-dimensional state spaces by aiming to reconstruct and predict the original observations. However, drawing inspiration from model-free reinforcement learning, we…

Training and fine-tuning deep learning models, especially large language models (LLMs), on limited and imbalanced datasets poses substantial challenges. These issues often result in poor generalization, where models overfit to dominant…

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent actions during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action…

A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability to predict the label via some method of generalisation. In…

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…

The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a better-than-random exploration policy or a safe-guard against…