Related papers: $\texttt{dattri}$: A Library for Efficient Data At…

Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is…

The development of the DRL model for malware attribution involved extensive research, iterative coding, and numerous adjustments based on the insights gathered from predecessor models and contemporary research papers. This preparatory work…

Attribution maps are popular tools for explaining neural networks predictions. By assigning an importance value to each input dimension that represents its impact towards the outcome, they give an intuitive explanation of the decision…

Despite the increasingly successful application of neural networks to many problems in the geosciences, their complex and nonlinear structure makes the interpretation of their predictions difficult, which limits model trust and does not…

With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual…

Modern ML systems increasingly augment input instances with additional relevant information to enhance final prediction. Despite growing interest in such retrieval-augmented models, their fundamental properties and training are not well…

We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset. Our framework considers…

Despite significant progress of applying deep learning methods to the field of content-based image retrieval, there has not been a software library that covers these methods in a unified manner. In order to fill this gap, we introduce…

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and…

Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference. In this work, we expand TTA to a more practical scenario, where the test…

In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However,…

The development of Generative AI Large Language Models (LLMs) raised the alarm regarding identifying content produced through generative AI or humans. In one case, issues arise when students heavily rely on such tools in a manner that can…

Deep learning has been widely applied in recommender systems, which has achieved revolutionary progress recently. However, most existing learning-based methods assume that the user and item distributions remain unchanged between the…

Recent advances on deep learning models come at the price of formidable training cost. The increasing model size is one of the root causes, but another less-emphasized fact is that data scale is actually increasing at a similar speed as…

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

Current models for quotation attribution in literary novels assume varying levels of available information in their training and test data, which poses a challenge for in-the-wild inference. Here, we approach quotation attribution as a set…

Object detectors frequently encounter significant performance degradation when confronted with domain gaps between collected data (source domain) and data from real-world applications (target domain). To address this task, numerous…

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…

There has been a recent push in making machine learning models more interpretable so that their performance can be trusted. Although successful, these methods have mostly focused on the deep learning methods while the fundamental…

Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity for a computer to learn from data accurately and efficiently…