Related papers: V3DB: Audit-on-Demand Zero-Knowledge Proofs for Ve…

Visual Document Retrieval (VDR), the task of retrieving visually-rich document pages using queries that combine visual and textual cues, is crucial for numerous real-world applications. Recent state-of-the-art methods leverage Large…

Large language models are often adapted through parameter efficient fine tuning, but current release practices provide weak assurances about what data were used and how updates were computed. We present Verifiable Fine Tuning, a protocol…

Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address the inherent non-determinism of deep learning. Stochastic…

Test case generation is an important activity, yet a time-consuming and laborious task. Recently, AthenaTest -- a deep learning approach for generating unit test cases -- is proposed. However, AthenaTest can generate less than one-fifth of…

Existing benchmarks for visual document retrieval (VDR) largely overlook non-English languages and the structural complexity of official publications. To address this gap, we introduce SDS KoPub VDR, the first large-scale, public benchmark…

Visual-semantic embedding is an interesting research topic because it is useful for various tasks, such as visual question answering (VQA), image-text retrieval, image captioning, and scene graph generation. In this paper, we focus on…

In this paper, we present BlinkDB, a massively parallel, sampling-based approximate query engine for running ad-hoc, interactive SQL queries on large volumes of data. The key insight that BlinkDB builds on is that one can often make…

Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results, missing the…

Despite remarkable progress in video generation, maintaining long-term scene consistency upon revisiting previously explored areas remains challenging. Existing solutions rely either on explicitly constructing 3D geometry, which suffers…

Medication errors pose a significant threat to patient safety, making pharmacist verification (PV) a critical, yet heavily burdened, final safeguard. The direct application of Large Language Models (LLMs) to this zero-tolerance domain is…

Modern text retrieval systems often provide a similarity search utility, that allows the user to find efficiently a fixed number k of documents in the data set that are most similar to a given query (here a query is either a simple sequence…

Cloud users (clients) with limited storage capacity at their end can outsource bulk data to the cloud storage server. A client can later access her data by downloading the required data files. However, a large fraction of the data files the…

Many applications require the immutable and consistent sharing of data across organizational boundaries. Because conventional datastores cannot provide this functionality, blockchains have been proposed as one possible solution. Yet public…

In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods. However, one of the significant challenges faced in this field is…

Data tampering is often considered a severe problem in industrial applications as it can lead to inaccurate financial reports or even a corporate security crisis. A correct representation of data is essential for companies' core business…

Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads to two major challenges: the lack of manual annotations for…

As online merchandise become more common, many studies focus on embedding-based methods where queries and products are represented in the semantic space. These methods alleviate the problem of vocab mismatch between the language of queries…

When validated neural networks (NNs) are pruned (and retrained) before deployment, it is desirable to prove that the new NN behaves equivalently to the (original) reference NN. To this end, our paper revisits the idea of differential…

Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…

Vector search has been widely employed in recommender system and retrieval-augmented-generation pipelines, commonly performed with vector indexes to efficiently find similar items in large datasets. Recent growths in both data and task…