相关论文: A Survey of Controllable Learning: Methods and App…

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common…

This survey provides an overview of combining Federated Learning (FL) and control to enhance adaptability, scalability, generalization, and privacy in (nonlinear) control applications. Traditional control methods rely on controller design…

Machine learning (ML) has emerged as a powerful tool for tackling complex regression and classification tasks, yet its success often hinges on the quality of training data. This study introduces an ML paradigm inspired by domain knowledge…

As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are,…

Graph machine learning has been extensively studied in both academia and industry. However, in the literature, most existing graph machine learning models are designed to conduct training with data samples in a random order, which may…

New technologies have led to vast troves of large and complex datasets across many scientific domains and industries. People routinely use machine learning techniques to not only process, visualize, and make predictions from this big data,…

Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-based methods have attracted significant attention, but they…

Continual Learning (CL) and Streaming Machine Learning (SML) study the ability of agents to learn from a stream of non-stationary data. Despite sharing some similarities, they address different and complementary challenges. While SML…

The learning rate is one of the most important hyperparameters in deep learning, and how to control it is an active area within both AutoML and deep learning research. Approaches for learning rate control span from classic optimization to…

Model evaluation is a critical component in supervised machine learning classification analyses. Traditional metrics do not currently incorporate case difficulty. This renders the classification results unbenchmarked for generalization.…

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…

Continual learning (CL) aims to train deep neural networks efficiently on streaming data while limiting the forgetting caused by new tasks. However, learning transferable knowledge with less interference between tasks is difficult, and…

Machine learning has attracted widespread attention and evolved into an enabling technology for a wide range of highly successful applications, such as intelligent computer vision, speech recognition, medical diagnosis, and more. Yet a…

Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these findings by asking why a model learns these disparate…

Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…

Online Continual Learning (OCL) is a critical area in machine learning, focusing on enabling models to adapt to evolving data streams in real-time while addressing challenges such as catastrophic forgetting and the stability-plasticity…

Strategic classification regards the problem of learning in settings where users can strategically modify their features to improve outcomes. This setting applies broadly and has received much recent attention. But despite its practical…

In-context learning (ICL) is a type of prompting where a transformer model operates on a sequence of (input, output) examples and performs inference on-the-fly. In this work, we formalize in-context learning as an algorithm learning problem…

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Controlling output length in neural language generation is valuable in many scenarios, especially for the tasks that have length constraints. A model with stronger length control capacity can produce sentences with more specific length,…