Related papers: Adaptive Constraint Propagation: Scaling Structure…
Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during…
Existing test-time scaling (TTS) methods for unified multimodal models (UMMs) in text-to-image (T2I) generation primarily rely on search or sampling strategies that produce only instance-level improvements, limiting the ability to learn…
This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to…
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of…
Reinforcement learning has become a powerful paradigm for improving the capability of intelligent systems, but its practical deployment faces two central challenges. First, reinforcement learning must scale efficiently in distributed…
Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…
Large language models (LLMs) have exhibited considerable cross-lingual generalization abilities, whereby they implicitly transfer knowledge across languages. However, the transfer is not equally successful for all languages, especially for…
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires…
Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning…
Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…
This paper considers methods for delivering ultra reliable low latency communication (URLLC) to enable mission-critical Internet of Things (IoT) services in wireless environments with unknown channel distribution. The methods rely upon the…
The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on…
While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge this gap but typically…
Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…
Despite remarkable achievements in artificial intelligence, the deployability of learning-enabled systems in high-stakes real-world environments still faces persistent challenges. For example, in safety-critical domains like autonomous…
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of…
Adapting large language models (LLMs) to unseen tasks with in-context training samples without fine-tuning remains an important research problem. To learn a robust LLM that adapts well to unseen tasks, multiple meta-training approaches have…
Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods…
Ensuring neural networks adhere to domain-specific constraints is crucial for addressing safety and trustworthiness while also enhancing inference accuracy. Despite the nonlinear nature of most real-world tasks, the majority of existing…
Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…