Related papers: BRIDGE: Multimodal-to-Text Retrieval via Reinforce…

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…

Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input. Often, such joint embeddings are learnt using pairwise (or triplet) contrastive loss…

Recent advances in multimodal large language models (LLMs) have led to significant progress in understanding, generation, and retrieval tasks. However, current solutions often treat these tasks in isolation or require training LLMs from…

Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive…

Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual…

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…

Retrieval-augmented generation (RAG) is a common way to ground language models in external documents and up-to-date information. Classical retrieval systems relied on lexical methods such as BM25, which rank documents by term overlap with…

Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document…

Retrieval-Augmented Generation (RAG) has gained prominence as an effective method for enhancing the generative capabilities of Large Language Models (LLMs) through the incorporation of external knowledge. However, the evaluation of RAG…

Mixture of Vision Encoders (MoVE) has emerged as a powerful approach to enhance the fine-grained visual understanding of multimodal large language models (MLLMs), improving their ability to handle tasks such as complex optical character…

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pseudo-evidence, while…

Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs often involve designing more powerful vision encoders, which…

We introduce StratRAG, an open-source retrieval evaluation dataset for benchmarking Retrieval-Augmented Generation (RAG) systems on multi-hop reasoning tasks under realistic, noisy document-pool conditions. Derived from HotpotQA (distractor…

Financial documents--such as 10-Ks, 10-Qs, and investor presentations--span hundreds of pages and combine diverse modalities, including dense narrative text, structured tables, and complex figures. Answering questions over such content…

Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on layout analysis and…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine…

Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (DocRAG) methods…

The choice of representation for geographic location significantly impacts the accuracy of models for a broad range of geospatial tasks, including fine-grained species classification, population density estimation, and biome classification.…

Recent advances in Retrieval-Augmented Generation (RAG) have significantly improved response accuracy and relevance by incorporating external knowledge into Large Language Models (LLMs). However, existing RAG methods primarily focus on…