Related papers: CodeXEmbed: A Generalist Embedding Model Family fo…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Retrieval over large codebases is a key component of modern LLM-based software engineering systems. Existing approaches predominantly rely on dense embedding models, while learned sparse retrieval (LSR) remains largely unexplored for code.…

Universal multimodal embedding models play a critical role in tasks such as interleaved image-text retrieval, multimodal RAG, and multimodal clustering. However, our empirical results indicate that existing LMM-based embedding models…

Motivated by the growing demand for retrieval systems that operate across modalities, we introduce llama-nemoretriever-colembed, a unified text-image retrieval model that delivers state-of-the-art performance across multiple benchmarks. We…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embedding space and retrieve results based on vector similarity. Despit strong…

Patent text embeddings enable prior art search, technology landscaping, and patent analysis, yet existing benchmarks inadequately capture patent-specific challenges. We introduce PatenTEB, a comprehensive benchmark comprising 15 tasks…

We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and…

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual…

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…

Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code…

Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically…

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

Code-mixing, the practice of switching between languages within a conversation, poses unique challenges for traditional NLP. Existing benchmarks are limited by their narrow language pairs and tasks, failing to adequately assess large…

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Recently, code language models have achieved notable advancements in addressing a diverse array of essential code comprehension and generation tasks. Yet, the field lacks a comprehensive deep dive and understanding of the code embeddings of…

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…

Utilizing large language models to generate codes has shown promising meaning in software development revolution. Despite the intelligence shown by the large language models, their specificity in code generation can still be improved due to…

The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering…

Retrieval-Augmented Generation (RAG) systems have been popular for generative applications, powering language models by injecting external knowledge. Companies have been trying to leverage their large catalog of documents (e.g. PDFs,…