Related papers: IRPAPERS: A Visual Document Benchmark for Scientif…

Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query…

Thanks to recent advancements in machine learning, vector-based methods have been adopted in many modern information retrieval (IR) systems. While showing promising retrieval performance, these approaches typically fail to explain why a…

The burgeoning integration of 3D medical imaging into healthcare has led to a substantial increase in the workload of medical professionals. To assist clinicians in their diagnostic processes and alleviate their workload, the development of…

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…

The Bing Bang of the Internet in the early 90's increased dramatically the number of images being distributed and shared over the web. As a result, image information retrieval systems were developed to index and retrieve image files spread…

Large Language Models (LLMs) have demonstrated impressive capabilities in answering questions, but they lack domain-specific knowledge and are prone to hallucinations. Retrieval Augmented Generation (RAG) is one approach to address these…

The volume of scientific literature is growing exponentially, leading to underutilized discoveries, duplicated efforts, and limited cross-disciplinary collaboration. Retrieval Augmented Generation (RAG) offers a way to assist scientists by…

Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain…

Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the…

Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking…

Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented -- focusing on either text or images in…

Developers increasingly rely on text matching tools to analyze the relation between natural language words and APIs. However, semantic gaps, namely textual mismatches between words and APIs, negatively affect these tools. Previous studies…

Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR.…

Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents. Combining large language models (LLMs) with embedding-based retrieval models, recent work shows promising results on…

Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity…

Latent text representations exhibit geometric regularities, such as the famous analogy: queen is to king what woman is to man. Such structured semantic relations were not demonstrated on image representations. Recent works aiming at…

Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such as pose and viewpoint. We proposeVisualize-then-Retrieve…

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

Enabling bi-directional retrieval of images and texts is important for understanding the correspondence between vision and language. Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner.…

Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, context-heavy documents and are not well captured by paragraph-only dense retrieval. We present…