Related papers: CoCoSoDa: Effective Contrastive Learning for Code …

Cross-lingual document search is an information retrieval task in which the queries' language differs from the documents' language. In this paper, we study the instability of neural document search models and propose a novel end-to-end…

Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a…

Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also becoming apparent. To test and evaluate for data extraction risks in LLM, we proposed…

Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code…

Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative model for learning…

A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using…

Effective code retrieval plays a crucial role in advancing code generation, bug fixing, and software maintenance, particularly as software systems increase in complexity. While current code embedding models have demonstrated promise in…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Momentum Contrast (MoCo) achieves great success for unsupervised visual representation. However, there are a lot of supervised and semi-supervised datasets, which are already labeled. To fully utilize the label annotations, we propose…

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive approaches remain…

While contrastive pre-training is widely employed, its data efficiency problem has remained relatively under-explored thus far. Existing methods often rely on static coreset selection algorithms to pre-identify important data for training.…

Self-supervised methods have shown tremendous success in the field of computer vision, including applications in remote sensing and medical imaging. Most popular contrastive-loss based methods like SimCLR, MoCo, MoCo-v2 use multiple views…

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

Contrastive-based self-supervised learning methods achieved great success in recent years. However, self-supervision requires extremely long training epochs (e.g., 800 epochs for MoCo v3) to achieve promising results, which is unacceptable…

Contrastive learning operates on a simple yet effective principle: Embeddings of positive pairs are pulled together, while those of negative pairs are pushed apart. In this paper, we propose a unified framework for understanding contrastive…

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…

We propose contrastive coding to learn shared, dense image representations, referred to as CoMIRs (Contrastive Multimodal Image Representations). CoMIRs enable the registration of multimodal images where existing registration methods often…

Translation between natural language and source code can help software development by enabling developers to comprehend, ideate, search, and write computer programs in natural language. Despite growing interest from the industry and the…