Related papers: Gemini Embedding: Generalizable Embeddings from Ge…

Large Language Models (LLMs) like ChatGPT, Copilot, Gemini, and DeepSeek are transforming software engineering by automating key tasks, including code generation, testing, and debugging. As these models become integral to development…

Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint representation in understanding and generation pipelines, high-quality…

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and…

This paper introduces the novel task of multimodal puzzle solving, framed within the context of visual question-answering. We present a new dataset, AlgoPuzzleVQA designed to challenge and evaluate the capabilities of multimodal language…

Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…

The advent of powerful, accessible Large Language Models (LLMs) like Google's Gemini presents new opportunities for democratizing financial data analysis. This paper documents the design, implementation, and iterative debugging of a novel,…

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…

Word embeddings have become a standard resource in the toolset of any Natural Language Processing practitioner. While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual…

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent and meaningless…

Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior work has shown that activation probes may be a promising misuse mitigation…

Automated sentiment analysis using Large Language Model (LLM)-based models like ChatGPT, Gemini or LLaMA2 is becoming widespread, both in academic research and in industrial applications. However, assessment and validation of their…

Learning high-quality embeddings for rare words is a hard problem because of sparse context information. Mimicking (Pinter et al., 2017) has been proposed as a solution: given embeddings learned by a standard algorithm, a model is first…

Embeddings mapping high-dimensional discrete input to lower-dimensional continuous vector spaces have been widely adopted in machine learning applications as a way to capture domain semantics. Interviewing 13 embedding users across…

Multilingual (or cross-lingual) embeddings represent several languages in a unique vector space. Using a common embedding space enables for a shared semantic between words from different languages. In this paper, we propose to embed images…

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

We present MMbeddings, a probabilistic embedding approach that reinterprets categorical embeddings through the lens of nonlinear mixed models, effectively bridging classical statistical theory with modern deep learning. By treating…

In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled…

Comparing human and model performance offers a valuable perspective for understanding the strengths and limitations of embedding models, highlighting where they succeed and where they fail to capture meaning and nuance. However, such…

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a…