相关论文: Daunce: Data Attribution through Uncertainty Estim…

Deep learning (DL) techniques have achieved great success in predictive accuracy in a variety of tasks, but deep neural networks (DNNs) are shown to produce highly overconfident scores for even abnormal samples. Well-defined uncertainty…

Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabilities, outperforming large datasets often burdened by…

Instruction tuning has underscored the significant potential of large language models (LLMs) in producing more human controllable and effective outputs in various domains. In this work, we focus on the data selection problem for…

Deep neural networks (DNNs) have been widely used in many fields such as images processing, speech recognition; however, they are vulnerable to adversarial examples, and this is a security issue worthy of attention. Because the training…

Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through…

Selecting appropriate training data is crucial for effective instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced performance across a diverse range of tasks.…

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data…

Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in safety-critical systems. In this study, we introduce a novel and efficient method for deterministic uncertainty estimation called Discriminant…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

Unsupervised domain adaptation~(UDA) aims at reducing the distribution discrepancy when transferring knowledge from a labeled source domain to an unlabeled target domain. Previous UDA methods assume that the source and target domains share…

Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling…

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…

Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra…

Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data in a source domain. Most deep UDA approaches operate in a…

Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature…

Large-scale diffusion neural networks represent a substantial milestone in text-to-image generation, but they remain poorly understood, lacking interpretability analyses. In this paper, we perform a text-image attribution analysis on Stable…

Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning…

Generative machine learning models offer a powerful framework for therapeutic design by efficiently exploring large spaces of biological sequences enriched for desirable properties. Unlike supervised learning methods, which require both…