Related papers: TSEmbed: Unlocking Task Scaling in Universal Multi…

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant…

Satellite imagery differs fundamentally from natural images: its aerial viewpoint, very high resolution, diverse scale variations, and abundance of small objects demand both region-level spatial reasoning and holistic scene understanding.…

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…

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…

Network Embedding has been widely studied to model and manage data in a variety of real-world applications. However, most existing works focus on networks with single-typed nodes or edges, with limited consideration of unbalanced…

Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance,…

Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often…

Embedding models are integral to AI applications like semantic search, personalized recommendations, and retrieval augmented generation for LLMs, necessitating high-quality training data. However, the limited scalability of manual data…

Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final token, typically a reserved special token such as [EOS].…

We propose a novel discriminative model that learns embeddings from multilingual and multi-modal data, meaning that our model can take advantage of images and descriptions in multiple languages to improve embedding quality. To that end, we…

Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance…

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…

Despite Multi-modal Large Language Models (MM-LLMs) have made exciting strides recently, they are still struggling to efficiently model the interactions among multi-modal inputs and the generation in non-textual modalities. In this work, we…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Distributional semantics based on neural approaches is a cornerstone of Natural Language Processing, with surprising connections to human meaning representation as well. Recent Transformer-based Language Models have proven capable of…

Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advances in large language models (LLMs) have further enhanced the performance of embedding models. While these models…

Much of human knowledge is encoded in text, available in scientific publications, books, and the web. Given the rapid growth of these resources, we need automated methods to extract such knowledge into machine-processable structures, such…

The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with…

Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computational complexity and storage requirements, thereby hindering…