Related papers: QueryPlot: Generating Geological Evidence Layers u…
The growing proliferation of customized and pretrained generative models has made it infeasible for a user to be fully cognizant of every model in existence. To address this need, we introduce the task of content-based model search: given a…
Knowledge-intensive language tasks (KILT) usually require a large body of information to provide correct answers. A popular paradigm to solve this problem is to combine a search system with a machine reader, where the former retrieves…
Text classification stands as a cornerstone within the realm of Natural Language Processing (NLP), particularly when viewed through computer science and engineering. The past decade has seen deep learning revolutionize text classification,…
Knowledge Graphs, such as Wikidata, comprise structural and textual knowledge in order to represent knowledge. For each of the two modalities dedicated approaches for graph embedding and language models learn patterns that allow for…
In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over single-vector approaches. However, its practical adoption is…
Existing large language models (LLMs) driven search agents typically rely on prompt engineering to decouple the user queries into search plans, limiting their effectiveness in complex scenarios requiring reasoning. Furthermore, they suffer…
We propose a new methodology to perform mineralogic inversion from wellbore logs based on a Bayesian linear regression model. Our method essentially relies on three steps. The first step makes use of Approximate Bayesian Computation (ABC)…
The words of a language reflect the structure of the human mind, allowing us to transmit thoughts between individuals. However, language can represent only a subset of our rich and detailed cognitive architecture. Here, we ask what kinds of…
Adopting Knowledge Graphs (KGs) as a structured, semantic-oriented, data representation model has significantly improved data integration, reasoning, and querying capabilities across different domains. This is especially true in modern…
This report presents our participation to the WSDM Cup 2026 shared task on multilingual document retrieval from English queries. The task provides a challenging benchmark for cross-lingual generalization. It also provides a natural testbed…
We propose a novel probabilistic dimensionality reduction framework that can naturally integrate the generative model and the locality information of data. Based on this framework, we present a new model, which is able to learn a smooth…
This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…
Traditional semantic image search methods aim to retrieve images that match the meaning of the text query. However, these methods typically search for objects on the whole image, without considering the localization of objects within the…
Knowledge-intensive visual question answering (VQA) requires external knowledge beyond image content, demanding precise visual grounding and coherent integration of visual and textual information. Although multimodal retrieval-augmented…
Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. Many researchers have incorporated different techniques to overcome the technical and domain specificity…
Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…
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…
Designing polymers for targeted applications and accurately predicting their properties is a key challenge in materials science owing to the vast and complex polymer chemical space. While molecular language models have proven effective in…
How to generate a large, realistic set of tables along with joinability relationships, to stress-test dataset discovery methods? Dataset discovery methods aim to automatically identify related data assets in a data lake. The development and…
Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to…