相关论文: SwiftEmbed: Ultra-Fast Text Embeddings via Static …

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be…

We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 tokens, making them…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Current sentence embedding evaluations typically rely on static test beds like the Massive Text Embedding Benchmark (MTEB). While invaluable, repeated tuning on a fixed suite can inflate reported scores and obscure real-world robustness. We…

In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We theoretically prove that our approach produces globally consistent representations in…

In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose ReMixer, a new data synthesis method that…

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text…

Text embeddings are typically evaluated on a limited set of tasks, which are constrained by language, domain, and task diversity. To address these limitations and provide a more comprehensive evaluation, we introduce the Massive…

This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication…

This paper introduces TurkEmbed, a novel Turkish language embedding model designed to outperform existing models, particularly in Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. Current Turkish embedding models…

Edge acceleration for large language models is crucial for their widespread application; however, achieving fast attention inference and efficient decoding on resource-constrained edge accelerators remains challenging. This paper presents…

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled…

In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training…

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…

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…

This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistral\footnote{\url{https://huggingface.co/Linq-AI-Research/Linq-Embed-Mistral}} by building on the…

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs. Word Embedding Methods (WEMs) are a class of representation learning methods that generate…