Related papers: Contrast-CAT: Contrasting Activations for Enhanced…

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…

Vision Transformers (ViTs) achieve strong performance in visual recognition, yet their decision-making remains difficult to interpret. We propose BiCAM, a bidirectional class activation mapping method that captures both supportive…

Common acquisition functions for active learning use either uncertainty or diversity sampling, aiming to select difficult and diverse data points from the pool of unlabeled data, respectively. In this work, leveraging the best of both…

In computer vision, contrastive learning is the most advanced unsupervised learning framework. Yet most previous methods simply apply fixed composition of data augmentations to improve data efficiency, which ignores the changes in their…

Accuracy and Diversity are two essential metrizable manifestations in generating natural and semantically correct captions. Many efforts have been made to enhance one of them with another decayed due to the trade-off gap. In this work, we…

The task-conditional model is a distinctive stream for efficient multi-task learning. Existing works encounter a critical limitation in learning task-agnostic and task-specific representations, primarily due to shortcomings in global…

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and…

As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although…

Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems…

When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulations. Decision trees such as CART provide clear and verifiable…

Although large-scale pretrained language models, such as BERT and RoBERTa, have achieved superhuman performance on in-distribution test sets, their performance suffers on out-of-distribution test sets (e.g., on contrast sets). Building…

One of the central goals of causal machine learning is the accurate estimation of heterogeneous treatment effects from observational data. In recent years, meta-learning has emerged as a flexible, model-agnostic paradigm for estimating…

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…

End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of…

We study offline meta-reinforcement learning, a practical reinforcement learning paradigm that learns from offline data to adapt to new tasks. The distribution of offline data is determined jointly by the behavior policy and the task.…

Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, debugging, and…

Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method that utilizes…

Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recently, after the…

Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools,…

There are not many large medical image datasets available. For these datasets, too small deep learning models can't learn useful features, so they don't work well due to underfitting, and too big models tend to overfit the limited data. As…