OpenAI Blog
Text and code embeddings by contrastive pre-training
Read the original on OpenAI Blog →The Flow has not summarised this story yet — read it at OpenAI Blog.
Related stories
arXiv AI
1d ago
Efficient Code Embeddings from Code Generation Models
arXiv:2508. 21290v2 Announce Type: replace-cross Abstract: jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages.
arXiv AI
1d ago
Invariant Pretraining for Robust Code Representations
arXiv:2608. 15412v1 Announce Type: cross Abstract: Encoder-based code representation models remain widely deployed for discriminative tasks such as clone detection and code classification, where their small size and low inference cost are decisive.
arXiv Machine Learning
Aug 11
LLM-Based Embeddings for Program Analysis and Optimization
arXiv:2608. 07894v1 Announce Type: new Abstract: Recent advances have highlighted the potential of machine learning, particularly Large Language Models (LLMs), for analyzing and optimizing programs.
Hugging Face Trending Papers
Jun 24
BitNet Text Embeddings
LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage.
arXiv Machine Learning
Jun 30
Contrastive vision-language learning with paraphrasing and negation
arXiv:2511. 16527v2 Announce Type: replace-cross Abstract: Contrastive vision-language models continue to be the dominant approach for image-text retrieval.
arXiv Machine Learning
1d ago
Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach
arXiv:2608. 15224v1 Announce Type: new Abstract: Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation.