相关论文: Improving QA Model Performance with Cartographic I…

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious…

Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training data, which severely limits the model performance especially…

The performance of Quantum Autoencoders (QAEs) in anomaly detection tasks is critically dependent on the choice of data embedding and ansatz design. This study explores the effects of three data embedding techniques, data re-uploading,…

Within the field of causal inference, we consider the problem of estimating heterogeneous treatment effects from data. We propose and validate a novel approach for learning feature representations to aid the estimation of the conditional…

Discriminative Feature Feedback is a setting proposed by Dastupta et al. (2018), which provides a protocol for interactive learning based on feature explanations that are provided by a human teacher. The features distinguish between the…

In this paper, we explore Annotation Artifacts - the phenomena wherein large pre-trained NLP models achieve high performance on benchmark datasets but do not actually "solve" the underlying task and instead rely on some dataset artifacts…

Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Particularly noteworthy is the challenge posed by catastrophic overfitting (CO) in this…

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…

Since the advent of autonomous driving technology, it has experienced remarkable progress over the last decade. However, most existing research still struggles to address the challenges posed by environments where multiple vehicles have to…

Digital pathology plays a vital role across modern medicine, offering critical insights for disease diagnosis, prognosis, and treatment. However, histopathology images often contain artifacts introduced during slide preparation and…

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…

We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle new features in test data without further retraining. The…

We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. This problem is made challenging by several ambiguities caused by transparencies, shape variations and partial occlusions,…

We present a method for expanding a dataset by incorporating knowledge from the wide distribution of pre-trained latent diffusion models. Data augmentations typically incorporate inductive biases about the image formation process into the…

Learning from demonstrations has emerged as a promising paradigm for end-to-end robot control, particularly when scaled to diverse and large datasets. However, the quality of demonstration data, often collected through human teleoperation,…

Large datasets have become commonplace in NLP research. However, the increased emphasis on data quantity has made it challenging to assess the quality of data. We introduce Data Maps---a model-based tool to characterize and diagnose…

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to…

Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs). However, accurately assessing the performance of these applications remains a…

In language model training, it is desirable to equip models with capabilities from various tasks. However, it is not clear how to directly obtain the right data mixtures for these capabilities as the relationship between data and tasks is…