Related papers: Contrastive Sets and Framing: A Case Study in Scie…

Contrastive explanations, where one decision is explained in contrast to another, are supposed to be closer to how humans explain a decision than non-contrastive explanations, where the decision is not necessarily referenced to an…

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are nonconsensual, as the…

Various research initiatives try to utilize the operational principles of organisms and brains to develop alternative, biologically inspired computing paradigms and artificial cognitive systems. This paper reviews key features of the…

This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and…

Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability. One flourishing approach is through counterfactual explanations, which provide…

As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to…

We propose a novel biologically-plausible solution to the credit assignment problem motivated by observations in the ventral visual pathway and trained deep neural networks. In both, representations of objects in the same category become…

Understanding self-supervised learning is important but challenging. Previous theoretical works study the role of pretraining losses, and view neural networks as general black boxes. However, the recent work of Saunshi et al. argues that…

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules…

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to boost the performance of various application tasks. These pretraining methods are frequently extended with…

Brain-computer interfaces (BCIs), is ways for electronic devices to communicate directly with the brain. For most medical-type brain-computer interface tasks, the activity of multiple units of neurons or local field potentials is sufficient…

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised…

Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we…

Researchers in physics education have advocated both for including modeling in science classrooms as well as promoting student engagement with sensemaking. These two processes facilitate the generation of new knowledge by connecting to…

This work presents code to procedurally generate examples for the ARC training tasks. For each of the 400 tasks, an example generator following the transformation logic of the original examples was created. In effect, the assumed underlying…

The significant progress in the development of Large Language Models has contributed to blurring the distinction between human and AI-generated text. The increasing pervasiveness of AI-generated text and the difficulty in detecting it poses…

We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific…

Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the…

Contrastive learning have been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, exiting methods that generate molecular views by…

The goal of this work is to localize sound sources in visual scenes with a self-supervised approach. Contrastive learning in the context of sound source localization leverages the natural correspondence between audio and visual signals…